CINXE.COM

<!doctype html> <html lang="en"> <head> <meta charset="utf-8"> <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no"> <title>Time Series Stock Market Predictions: Using Time Interval Trigger</title> <meta name="keywords" content="Stock market; Price prediction; Lower bound; Upper bound; Time interval triggered; Flag attribute; Time series data"> <meta name="description" content="Despite being one of the most widely used techniques of financial management, stocks have drawn increasing numbers of investors during recent years. A subs.. "/> <meta name="citation_publisher" content="Longdom Publishing S.L"/> <meta name="citation_journal_title" content="Journal of Stock & Forex Trading"> <meta name="citation_title" content="Time Series Stock Market Predictions: Using Time Interval Triggered of Flag Attribute Model in Deep Learning"> <meta name="citation_author" content="Sudhakar Kalva"/> <meta name="citation_author" content="Naganjaneyulu Satuluri"/> <meta name="citation_year" content="2024"> <meta name="citation_volume" content="11"> <meta name="citation_issue" content="1"> <meta name="citation_doi" content="10.35248/2168-9458.24.11.249"> <meta name="citation_issn" content="2168-9458"> <meta name="citation_publication_date" content="2024/03/01"/> <meta name="citation_firstpage" content="1"> <meta name="citation_lastpage" content="8"> <meta name="citation_abstract" content="Despite being one of the most widely used techniques of financial management, stocks have drawn increasing numbers of investors during recent years. A substantial degree of risk is involved in buying stocks. The foremost concern for investors is how to minimize risks and maximize returns. One of the most common issues in the stock market is predicting a company's stock value. Volatility in individual profits and the health of the economy are negatively impacted by fluctuations in stock prices. One of the most widely held beliefs among humans is that investing in stock markets, which are supposed to produce excellent outcomes, is one of the finest ways to generate money. Volatility in stock market prices can occur for a variety of causes. It fosters an environment of uncertainty, which discourages constructive investment. Stock markets are notorious for their volatility. Those who are directly or indirectly involved in stock markets should be aware of it. It is necessary to create an intelligent system that can make forecasts based on a variety of indications such as fundamental, statistical, and technical trends. However, no single good predictive model has ever been able to consistently outperform market patterns. Traditionally, predictions for time series data have been made based on previous data and market trends, as well as historical correlation data and projections. Above all, there is no system that calculates projections based on a user's choice of investment type and risk tolerance. The main focus of this research work is on predicting stock market price changes. Instead of looking at daily changes, this research examines the price trend over specific time intervals by identifying turning points. To determine the increasing trend of price change, deep neural network model is used for accurate predictions. In this research work, an Efficient Time Series Stock Market Predictions using Time Interval Triggered Flag Attribute Model (ETSSMP-TITFA) using deep learning is proposed that predicts the lower bound and upper bound of stock market price predictions of multiple companies. The proposed model is contrasted with the traditional models and the results represent that the proposed model performance is better."> <meta name="citation_fulltext_html_url" content="https://www.longdom.org/open-access/time-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning-106618.html"> <meta name="citation_pdf_url" content="https://www.longdom.org/open-access/time-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning.pdf"> <meta name="citation_abstract_html_url" content="https://www.longdom.org/abstract/time-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning-106618.html"> <meta name="format-detection" content="telephone=no" /> <meta name="google-site-verification" content="NomPTP94YozsgvD3NEFpNqUfY88e0TU0L64zNzZTpd0" /> <meta itemprop="name" content="longdom" /> <meta http-equiv="X-UA-Compatible" content="IE=edge" /> <meta name="ROBOTS" content="INDEX,FOLLOW" /> <meta name="googlebot" content="INDEX,FOLLOW" /> <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no" /> <link rel="canonical" href="https://www.longdom.org/open-access/time-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning-106618.html" /> <link rel="alternate" href="https://www.longdom.org/open-access/time-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning-106618.html" hreflang="en-us" /> <script type="application/ld+json"> { "@context": "https://schema.org", "@type": "Organization", "url": "https://www.longdom.org/open-access/time-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning-106618.html", "logo": "https://www.longdom.org/assets/img/longdom-logo.svg" } </script>  <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.3.1/css/bootstrap.min.css" /> <link href="/assets/css/longdom.css" rel="stylesheet" /> <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/animate.css/3.7.0/animate.min.css" />  <link rel="stylesheet" href="https://use.fontawesome.com/releases/v5.7.1/css/all.css" /> <link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.3.0/css/font-awesome.min.css" />  <link href="https://fonts.googleapis.com/css?family=Montserrat:100,100i,200,200i,300,300i,400,400i,500,500i,600,600i,700,700i,800,800i,900,900i|Open+Sans:300,300i,400,400i,600,600i,700,700i,800,800i|Raleway:100,100i,200,200i,300,300i,400,400i,500,500i,600,600i,700,700i,800,800i,900,900i" rel="stylesheet" /> <link href="/assets/css/ionicons.min.css" rel="stylesheet" />  <link rel="stylesheet" href="/assets/css/jquery.mCustomScrollbar.min.css" /> <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/bootstrap-select/1.13.2/css/bootstrap-select.min.css" />  <link rel="stylesheet" href="/assets/css/global.css" />  <link rel="stylesheet" href="/assets/css/styles.css" /> <link rel="stylesheet" type="text/css" href="/assets/css/author.css" /> <link rel="icon" href="/assets/img/favicon.png" type="image/gif" /> <link rel="stylesheet" href="/assets/css/coolautosuggest.css" />   <script async src="https://www.googletagmanager.com/gtag/js?id=G-LE7WH45F9C"></script> <script> window.dataLayer = window.dataLayer || []; function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); gtag('config', 'G-LE7WH45F9C'); </script> <meta property="og:title" content="Longdom Publishing SL | Open Access Journals" /> <meta property="og:site_name" content="Longdom" /> <meta property="og:url" content="https://www.longdom.org/" /> <meta property="og:description" content="Longdom Publishing SL is one of the leading international open access journals publishers, covering clinical, medical, and technology-oriented subjects" /> <meta property="og:type" content="article" /> <meta property="og:image" content="https://www.longdom.org/assets/img/longdom-logo.svg" /> <meta name="twitter:card" content="summary" /> <meta name="twitter:site" content="@org_longdom" /> <meta name="twitter:title" content="Longdom Publishing SL | Open Access Journals" /> <meta name="twitter:description" content="Longdom Publishing SL is one of the leading international open access journals publishers, covering clinical, medical, and technology-oriented subjects." /> <meta name="twitter:image" content="https://www.longdom.org/assets/img/longdom-logo.svg" />  <script> !function(f,b,e,v,n,t,s){if(f.fbq)return;n=f.fbq=function(){n.callMethod? n.callMethod.apply(n,arguments):n.queue.push(arguments)};if(!f._fbq)f._fbq=n; n.push=n;n.loaded=!0;n.version='2.0';n.queue=[];t=b.createElement(e);t.async=!0; t.src=v;s=b.getElementsByTagName(e)[0];s.parentNode.insertBefore(t,s)}(window, document,'script','//connect.facebook.net/en_US/fbevents.js'); fbq('init', '297919997051754'); fbq('track', "PageView"); </script>  <script type="text/javascript"> function openimage( theURL, winName, features ) { window.open( theURL, winName, features ); } </script> </head> <body> <header>  <nav class="navbar navbar-expand-lg navbar-light bg-white shadow-sm deva541"> <div class="container"> <a class="navbar-brand" href="https://www.longdom.org/" title="Longdom Publishing S.L"> <img src="/assets/img/longdom-logo.svg" alt="" height="25"> </a> <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation"> <span class="navbar-toggler-icon"></span> </button> <div class="collapse navbar-collapse justify-content-end" id="navbar"> <div class="navbar-nav"> <a class="nav-item nav-link" href="https://www.longdom.org/" title="Home">Home</a> <div class="nav-item dropdown"> <a class="nav-link dropdown-toggle" href="#" id="Guidelines" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Journals</a> <div class="dropdown-menu" aria-labelledby="Journals"> <a class="dropdown-item" href="https://www.longdom.org/journals-by-title.html" title="A-Z Journals">A-Z Journals</a> <a class="dropdown-item" href="https://www.longdom.org/open-access-journals-list.html" title="Browse By Subject">Browse By Subject</a> </div> </div> <div class="nav-item dropdown"> <a class="nav-link dropdown-toggle" href="#" id="Guidelines" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Guidelines & Policies </a> <div class="dropdown-menu" aria-labelledby="Guidelines"> <a class="dropdown-item" href="https://www.longdom.org/editorial-policies.html" title="Editorial Policies">Editorial Policies</a> <a class="dropdown-item" href="https://www.longdom.org/submit-manuscript.html" title="Online Submission">Online Submission</a> <a class="dropdown-item" href="https://www.longdom.org/instructions-to-authors.html" title="Instructions to Authors">Instructions to Authors</a> <a class="dropdown-item" href="https://www.longdom.org/policies.html" title="Policies">Policies</a> <a class="dropdown-item" href="https://www.longdom.org/publication-ethics.html" title="Publication ethics & malpractice statement">Publication ethics & malpractice statement</a> <a class="dropdown-item" href="https://www.longdom.org/reviewers.html" title="Reviewers">Reviewers</a> <a class="dropdown-item" href="https://www.longdom.org/terms-conditions.html" title="Terms and Conditions">Terms and Conditions</a> </div> </div> <a class="nav-item nav-link" href="https://www.longdom.org/advertising.html" title="Advertising">Advertising</a> <a class="nav-item nav-link" href="https://www.longdom.org/conferences.html" title="Conferences">Conferences</a> <a class="nav-item nav-link" href="https://www.longdom.org/contact-us.html" title="Contact us">Contact us</a> <div id="google_translate_element"></div> </div>  </div> </div> </nav> </header>  <section class="bg-info py-1"> <div class="container"> <div class="row align-items-center justify-content-between">  <div class="col-12 col-sm-auto"> <img src="https://www.longdom.org/admin/headers/journal-of-stock--forex-trading-logo.svg" alt="Journal of Stock & Forex Trading" width="105" height="105" class="img-fluid mx-auto"> </div> <div class="col-12 col-sm-8"> <h1 class="text-left text-white border-light-blue-200-before font-size-7">Journal of Stock & Forex Trading<br><small class="float-right font-size-5">Open Access</small></h1> </div>  <div class="col-12 col-sm-2 d-none d-sm-block"> <p class="lead">ISSN: 2168-9458</p>  <div id="feedback" class="card card-body p-1 font-size-2 shadow-sm z-index-1"> <div class="reach-us-animated"></div> <p class="card-text"><img src="/assets/img/whatsapp.svg" alt="" width="20" class="ml-2"> +44 1223 790975</p> </div> </div> </div> </div> </section>  <nav id="sticky-navbar" class="navbar navbar-expand-lg navbar-dark bg-primary py-0"> <div class="container"> <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#jrnlNavbar" aria-controls="jrnlNavbar" aria-expanded="false" aria-label="Toggle navigation"> <span class="navbar-toggler-icon"></span> </button> <div class="collapse navbar-collapse justify-content-center" id="jrnlNavbar"> <div class="navbar-nav"> <a class="nav-item nav-link " href="https://www.longdom.org/stock-forex-trading.html" title="Journal Home">Journal Home</a> <div class="nav-item dropdown"> <a class="nav-link dropdown-toggle " href="#" id="EditorialPanel" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Editorial Panel <i class="fas fa-caret-down"></i></a> <div class="dropdown-menu" aria-labelledby="EditorialPanel"> <a class="dropdown-item" href="https://www.longdom.org/stock-forex-trading/editor-in-chief.html" title="Editor-in-Chief">Editor-in-Chief</a> <a class="dropdown-item" href="https://www.longdom.org/stock-forex-trading/editorial-board.html" title="Editorial Board">Editorial Board</a> </div> </div> <div class="nav-item dropdown"> <a class="nav-link dropdown-toggle " title="Instructions for Authors" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false" href="#">Instructions for Authors <i class="fas fa-caret-down"></i></a> <div class="dropdown-menu" aria-labelledby="EditorialPanel"> <a class="dropdown-item" href="https://www.longdom.org/stock-forex-trading/instructionsforauthors.html" title="Instructions for Authors">Instructions for Authors</a>  <a class="dropdown-item" href="https://www.longdom.org/stock-forex-trading/ethical-malpractices.html" title="Publication ethics & malpractice statement">Publication ethics & malpractice statement</a> </div> </div> <a class="nav-link " href="https://www.longdom.org/stock-forex-trading/submit-manuscript.html" title="Submit Manuscript">Submit Manuscript</a> <a class="nav-link " href="https://www.longdom.org/stock-forex-trading/aim-and-scope.html" title="Aims and Scope">Aims and Scope</a> <a class="nav-link " href="https://www.longdom.org/stock-forex-trading/inpress.html" title="Articles in process">Articles in process</a>  <a class="nav-link " href="https://www.longdom.org/stock-forex-trading/archive.html" title="Archive">Archive</a> <div class="nav-item dropdown"> <a class="nav-link dropdown-toggle " href="#" id="SpecialIssues" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Special Issues <i class="fas fa-caret-down"></i></a> <div class="dropdown-menu" aria-labelledby="SpecialIssues"> <a class="dropdown-item" href="https://www.longdom.org/stock-forex-trading/guidelines.html" title="Guidelines">Guidelines</a> <a class="dropdown-item" href="https://www.longdom.org/stock-forex-trading/upcoming-special-issues.html" title="Upcoming Special Issues">Upcoming Special Issues</a> </div> </div> <a class="nav-item nav-link " href="https://www.longdom.org/stock-forex-trading/contact.html" title="Contact">Contact</a> </div> </div> </div> </nav> <script type="text/javascript"> function googleTranslateElementInit() { new google.translate.TranslateElement({pageLanguage: 'en'}, 'google_translate_element'); } </script> <script type="text/javascript" src="//translate.google.com/translate_a/element.js?cb=googleTranslateElementInit"></script> <section class="py-4 content"> <div class="container"> <div class="row"> <aside class="col-12 col-sm-3 order-last order-sm-first"> <a href="https://www.longdom.org/stock-forex-trading/awards-nomination.html" class="btn btn-info btn-block mb-3 border-0 border-left-4 border-info font-size-4"><i class="fa-light fa-award-simple"></i> Awards Nomination </a> <a href="https://www.longdom.org/stock-forex-trading-online-visitors-readers-270.html" class="btn btn-warning btn-block mb-3 border-0 border-left-4 border-info font-size-4"><i class="fas fa-book-reader"></i> 25+ Million Readerbase</a>  <div class="card shadow-sm sidebar mb-3"> <div class="list-group list-group-flush qr_code_image"> <img title="QR" src="https://chart.googleapis.com/chart?chs=185x185&cht=qr&chl=https%3A%2F%2Fwww.longdom.org%2Fopen-access%2Ftime-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning-106618.html&chld=M|0&icqrf=00b1e4" alt="Longdom"/>  <nav class="nav nav-pills social-icons-footer sidebar_social_icons a-pl-0"> <a title="Share This Article" target="_blank" class="nav-link" rel="noopener" href="https://www.facebook.com/sharer.php?s=100&p[title]=Time Series Stock Market Predictions: Using Time Interval Triggered of Flag Attribute Model in Deep Learning&p[url]=https%3A%2F%2Fwww.longdom.org%2Fopen-access%2Ftime-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning-106618.html"><img src="https://www.longdom.org/assets/socials/facebook.png" alt="Longdom" /></a> <a title="Share This Article" target="_blank" class="nav-link" rel="noopener" href="https://web.whatsapp.com/send?text=https%3A%2F%2Fwww.longdom.org%2Fopen-access%2Ftime-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning-106618.html" title="Share This Article" target="_blank" class="nav-link"><img src="https://www.longdom.org/assets/socials/whatsapp.png" alt="Longdom"/></a> <a title="Share This Article" target="_blank" class="nav-link" rel="noopener" href="https://www.linkedin.com/sharing/share-offsite/?url=https%3A%2F%2Fwww.longdom.org%2Fopen-access%2Ftime-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning-106618.html" title="Share This Article" target="_blank" class="nav-link"><img src="https://www.longdom.org/assets/socials/linkedin.png" alt="Longdom"/></a> <a title="Share This Article" target="_blank" class="nav-link" rel="noopener" href="https://twitter.com/share?text=Time Series Stock Market Predictions: Using Time Interval Triggered of Flag Attribute Model in Deep Learning&url=https%3A%2F%2Fwww.longdom.org%2Fopen-access%2Ftime-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning-106618.html" class="nav-link"><img src="https://www.longdom.org/assets/socials/twitter.png" alt="Longdom" /></a> </nav>  </div> </div>     <h6><a target="_blank" href="https://scholar.google.com/citations?user=Tbm8VZgAAAAJ&hl=en" title="Click here">Google Scholar citation report</a></h6> <h6 style="font-weight:bold;">Citations : 813</h6> <p><a target="_blank" href="https://scholar.google.com/citations?user=Tbm8VZgAAAAJ&hl=en" title="Click here">Journal of Stock & Forex Trading received 813 citations as per Google Scholar report</a></p> <div class="card shadow-sm sidebar mb-3"> <a href="https://www.longdom.org/stock-forex-trading/citations.html" title="Click here"><img src="https://www.longdom.org/admin/citation-images/journal-of-stock--forex-trading-citation.png" alt="Citation" class="img-fluid p_rel" /></a> </div> <h6><a href="https://publons.com/journal/76137/journal-of-stock-forex-trading/" target="_blank" title="Click here">Journal of Stock & Forex Trading peer review process verified at publons</a></h6> <div class="card shadow-sm sidebar mb-3"> <a href="https://publons.com/journal/76137/journal-of-stock-forex-trading/" target="_blank" title="Click here"><img src="https://www.longdom.org/admin/publon-images/journal-of-stock--forex-trading-publon.png" alt="Flyer image" class="p_rel w-100" height="250px"/></a> </div>   <div class="card shadow-sm sidebar mb-3"> <h6 class="card-header pr-0">Indexed In</h6> <div class="list-group list-group-flush overflow-view"> <div class="list-group-item p-0 pt-2 pl-2"> <i class="fa fa-chevron-right" style="font-size: 11px;color: #0056b3;"></i> Open J Gate </div> <div class="list-group-item p-0 pt-2 pl-2"> <i class="fa fa-chevron-right" style="font-size: 11px;color: #0056b3;"></i> Genamics JournalSeek </div> <div class="list-group-item p-0 pt-2 pl-2"> <i class="fa fa-chevron-right" style="font-size: 11px;color: #0056b3;"></i> Academic Keys </div> <div class="list-group-item p-0 pt-2 pl-2"> <i class="fa fa-chevron-right" style="font-size: 11px;color: #0056b3;"></i> JournalTOCs </div> <div class="list-group-item p-0 pt-2 pl-2"> <i class="fa fa-chevron-right" style="font-size: 11px;color: #0056b3;"></i> China National Knowledge Infrastructure (CNKI) </div> <div class="list-group-item p-0 pt-2 pl-2"> <i class="fa fa-chevron-right" style="font-size: 11px;color: #0056b3;"></i> RefSeek </div> <div class="list-group-item p-0 pt-2 pl-2"> <i class="fa fa-chevron-right" style="font-size: 11px;color: #0056b3;"></i> Directory of Research Journal Indexing (DRJI) </div> <div class="list-group-item p-0 pt-2 pl-2"> <i class="fa fa-chevron-right" style="font-size: 11px;color: #0056b3;"></i> Hamdard University </div> <div class="list-group-item p-0 pt-2 pl-2"> <i class="fa fa-chevron-right" style="font-size: 11px;color: #0056b3;"></i> EBSCO A-Z </div> <div class="list-group-item p-0 pt-2 pl-2"> <i class="fa fa-chevron-right" style="font-size: 11px;color: #0056b3;"></i> OCLC- WorldCat </div> <div class="list-group-item p-0 pt-2 pl-2"> <i class="fa fa-chevron-right" style="font-size: 11px;color: #0056b3;"></i> Scholarsteer </div> <div class="list-group-item p-0 pt-2 pl-2"> <i class="fa fa-chevron-right" style="font-size: 11px;color: #0056b3;"></i> Publons </div> <div class="list-group-item p-0 pt-2 pl-2"> <i class="fa fa-chevron-right" style="font-size: 11px;color: #0056b3;"></i> Google Scholar </div> </div> <p class="m-0 clearfix"><a href="https://www.longdom.org/stock-forex-trading/indexing.html" title="Click here"><span class="btn btn-warning btn-xs float-right">View More »</span></a></p> </div>   <div class="card shadow-sm sidebar mb-3"> <h6 class="card-header">Useful Links</h6> <div class="card-body p-0"> <nav class="nav flex-column font-size-3 icon-list icon-list-angle-right a-py-1"> <a class="nav-item nav-link" href="https://www.longdom.org/covid-19-peer-reviewed-journals-articles-special-issues.html" title="Click Here">Covid-19 Journal Articles Issues</a> <a class="nav-item nav-link" href="https://www.longdom.org/stock-forex-trading/aim-and-scope.html" title="Click Here">Aim and Scope</a> <a class="nav-item nav-link" href="https://www.longdom.org/stock-forex-trading/peer-review-process.html" title="Click Here">Peer Review Process</a> <a class="nav-item nav-link" href="https://www.longdom.org/stock-forex-trading/other-comments.html" title="Click Here">Other Comments</a> <a class="nav-item nav-link" href="https://www.longdom.org/stock-forex-trading/advertising.html" title="Click Here">Advertising</a> <a class="nav-item nav-link" href="https://www.longdom.org/stock-forex-trading/citations.html" title="Click Here">Citations Report</a> <a class="nav-item nav-link" href="https://www.longdom.org/stock-forex-trading/indexing.html" title="Click Here">Indexing and Archiving</a> <a class="nav-item nav-link" href="https://www.longdom.org/stock-forex-trading/archive.html" title="Click Here">Table of Contents</a> <a class="nav-item nav-link" href="https://www.longdom.org/submissions/stock-forex-trading.html" title="Click Here">Submit Paper</a> <a class="nav-item nav-link" href="https://www.longdom.org/editorial-tracking/" title="Click Here">Track Your Paper</a> <a class="nav-item nav-link" href="https://www.longdom.org/funded-articles.html" title="Click Here">Funded Work</a> </nav> </div> </div>  <div class="card shadow-sm sidebar mb-3" style="margin-top:10px"> <h6 class="card-header">Share This Page</h6> <div class="card-body"> <nav class="nav social-icons social-icons-sm"> <a class="nav-link bg-facebook white" href="https://www.facebook.com/sharer.php?u=https://www.longdom.org/open-access/time-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning-106618.html" target="_blank" title="Share with Facebook" rel="noopener"><i class="fab fa-facebook-f"></i></a> <a class="nav-link bg-twitter white" href="https://twitter.com/share?url=https://www.longdom.org/open-access/time-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning-106618.html" rel="noopener" target="_blank" title="Share with Twitter"><i class="fab fa-twitter"></i></a> <a class="nav-link bg-linkedin white" href="https://www.linkedin.com/shareArticle?mini=true&url=https://www.longdom.org/open-access/time-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning-106618.html" rel="noopener" target="_blank" title="Share with Linkdin"><i class="fab fa-linkedin-in"></i></a> <a class="nav-link bg-googleplus white" href="https://plus.google.com/share?url=https://www.longdom.org/open-access/time-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning-106618.html" target="_blank" rel="noopener" title="Share with Google+"><i class="fab fa-google-plus-g"></i></a> <a class="nav-link bg-pinterest white" href="https://pinterest.com/pin/create/button/?url=https://www.longdom.org/open-access/time-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning-106618.html" rel="noopener" target="_blank" title="Share with Pintrest"><i class="fab fa-pinterest-p"></i></a> <a class="nav-link bg-blogger white" href="https://www.blogger.com/blog-this.g?u=https://www.longdom.org/open-access/time-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning-106618.html" rel="noopener" target="_blank" title="Share with Blogger"><i class="fab fa-blogger-b"></i></a> </nav> </div> </div>  <div class="card shadow-sm sidebar mb-3"> <h6 class="card-header">Recommended Journals</h6> <div class="card-body p-0"> <nav class="nav flex-column font-size-3 icon-list icon-list-angle-right a-py-1"> <a class="nav-item nav-link" href="https://www.longdom.org/hotel-business-management.html" title="Click Here">Business Journal</a> </nav> </div> </div>  <div class="card shadow-sm sidebar mb-3"> <a href="https://www.longdom.org/stock-forex-trading/advertising.html" title="Click here"><img src="https://www.longdom.org/assets/img/tower-banner.jpg" alt="Flyer image" class="img-fluid p_rel" /> <span class="p_abo cu_roundchip"> <span> <h5><span>25+</span> Million Website Visitors</h5> </span> </span> </a> </div>    <div class="card shadow-sm sidebar mb-3"> <h6 class="card-header">Journal Flyer</h6> <img src="https://www.longdom.org/admin/flyers/journal-of-stock--forex-trading-flyer.jpg" alt="Journal of Stock & Forex Trading" class="img-fluid"/> </div>   <div class="sidebar pt-20 pl-10 mt-xs-0" align="center"> <a class="twitter-timeline" href="https://twitter.com/ForexTradingJ" data-width="450" data-height="300">Tweets by ForexTradingJ</a> <script async src="https://platform.twitter.com/widgets.js" charset="utf-8"></script> </div> <div class="clear"> </div>   <div class="card shadow-sm sidebar mb-3"> <h6 class="card-header">Open Access Journals</h6> <div class="card-body p-0 scroll_mang"> <nav class="nav flex-column font-size-3 icon-list icon-list-angle-right a-py-1"> <a class="nav-item nav-link" href="https://www.longdom.org/agri-and-aquaculture-journals.html" title="Click Here">Agri and Aquaculture</a> <a class="nav-item nav-link" href="https://www.longdom.org/biochemistry-journals.html" title="Click Here">Biochemistry</a> <a class="nav-item nav-link" href="https://www.longdom.org/bioinformatics-and-systems-biology-journals.html" title="Click Here">Bioinformatics & Systems Biology</a> <a class="nav-item nav-link" href="https://www.longdom.org/business-and-management-journals.html" title="Click Here">Business & Management</a> <a class="nav-item nav-link" href="https://www.longdom.org/chemistry-journals.html" title="Click Here">Chemistry</a> <a class="nav-item nav-link" href="https://www.longdom.org/clinical-sciences-journals.html" title="Click Here">Clinical Sciences</a> <a class="nav-item nav-link" href="https://www.longdom.org/engineering-journals.html" title="Click Here">Engineering</a> <a class="nav-item nav-link" href="https://www.longdom.org/food-and-nutrition-journals.html" title="Click Here">Food & Nutrition</a> <a class="nav-item nav-link" href="https://www.longdom.org/general-science-journals.html" title="Click Here">General Science</a> <a class="nav-item nav-link" href="https://www.longdom.org/genetics-and-molecular-biology-journals.html" title="Click Here">Genetics & Molecular Biology</a> <a class="nav-item nav-link" href="https://www.longdom.org/immunology-and-microbiology-journals.html" title="Click Here">Immunology & Microbiology</a> <a class="nav-item nav-link" href="https://www.longdom.org/medical-sciences-journals.html" title="Click Here">Medical Sciences</a> <a class="nav-item nav-link" href="https://www.longdom.org/neuroscience-and-psychology-journals.html" title="Click Here">Neuroscience & Psychology</a> <a class="nav-item nav-link" href="https://www.longdom.org/nursing-and-health-care-journals.html" title="Click Here">Nursing & Health Care</a> <a class="nav-item nav-link" href="https://www.longdom.org/pharmaceutical-sciences-journals.html" title="Click Here">Pharmaceutical Sciences</a> </nav> </div> </div>  </aside> <div class="col-12 col-sm-9 full-text"> <div class="row align-items-center justify-content-between"> <div class="col-12 col-sm-4"> <p class="text-muted mb-0"> Research Article - (2024)Volume 11, Issue 1 </p> </div> <div class="col-12 col-sm-8 text-right custom-column"> <a href="https://www.longdom.org/open-access/time-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning.pdf" title="View PDF" class="btn btn-sm bg-green-600 rounded-50"><i class="fas fa-file-pdf"></i> View PDF</a> <a href="https://www.longdom.org/pdfdownload.php?download=open-access/time-series-stock-market-predictions-using-time-interval-triggered-of-flag-attribute-model-in-deep-learning.pdf&aid=106618" title="Download PDF" class="btn btn-sm bg-green-600 rounded-50"><i class="fas fa-download"></i> Download PDF</a> </div> </div> <h2 class="font-size-7 mt-2">Time Series Stock Market Predictions: Using Time Interval Triggered of Flag Attribute Model in Deep Learning</h2> <a href='https://www.longdom.org/author/sudhakar-kalva-67001' title='Sudhakar Kalva' style='color:#555; border-bottom:1px dotted #CCC;'>Sudhakar Kalva</a><sup><a href='#a1'>1</a></sup><sup><a href='#Sudhakar_Kalva'>*</a></sup> and <a href='https://www.longdom.org/author/naganjaneyulu-satuluri-67003' title='Naganjaneyulu Satuluri' style='color:#555; border-bottom:1px dotted #CCC;'>Naganjaneyulu Satuluri</a><sup><a href='#a2'>2</a></sup> <div> </div> <a id="Sudhakar_Kalva"></a> <strong><sup>*</sup>Correspondence:</strong> Sudhakar Kalva, Department of Computer Science and Engineering, Jawaharlal Nehru Technological University, Kakinada, Andhra Pradesh, India, <strong>Email:</strong> <i class='fa fa-envelope' aria-hidden='true' title='Sudhakarcs14@gmail.com'></i> <p><a href="#ai"><strong>Author info »</strong></a></p> <div class="card bg-light mb-3"> <div class="card-body px-3 pb-0"> <h2 class="font-size-5">Abstract</h2> <p>Despite being one of the most widely used techniques of financial management, stocks have drawn increasing numbers of investors during recent years. A substantial degree of risk is involved in buying stocks. The foremost concern for investors is how to minimize risks and maximize returns. One of the most common issues in the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> is predicting a company's <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> value. Volatility in individual profits and the health of the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/economy-53220.html'>economy</a> are negatively impacted by fluctuations in <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> prices. One of the most widely held beliefs among humans is that investing in <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> markets, which are supposed to produce excellent outcomes, is one of the finest ways to generate money. Volatility in <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> prices can occur for a variety of causes. It fosters an environment of uncertainty, which discourages constructive investment. <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>Stock</a> markets are notorious for their volatility. Those who are directly or indirectly involved in <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> markets should be aware of it. It is necessary to create an intelligent system that can make forecasts based on a variety of indications such as fundamental, statistical, and technical trends. However, no single good predictive model has ever been able to consistently outperform market patterns. Traditionally, predictions for time series data have been made based on previous data and market trends, as well as historical correlation data and projections. Above all, there is no system that calculates projections based on a user's choice of investment type and risk tolerance. The main focus of this research work is on predicting <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> price changes. Instead of looking at daily changes, this research examines the price trend over specific time intervals by identifying turning points. To determine the increasing trend of price change, deep neural network model is used for accurate predictions. In this research work, an Efficient Time Series <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>Stock Market</a> Predictions using Time Interval Triggered Flag Attribute Model (ETSSMP-TITFA) using deep learning is proposed that predicts the lower bound and upper bound of <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> price predictions of multiple companies. The proposed model is contrasted with the traditional models and the results represent that the proposed model performance is better.</p> <h4 class="font-size-4">Keywords</h4> <p>Stock market; Price prediction; Lower bound; Upper bound; Time interval triggered; Flag attribute; Time series data</p> </div> </div> <h4>Introduction</h4> <p>The <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> does more than only mobilise new capital in a country's economy. Because of its diverse set of critical services that drive capital accumulation and contribute to productivity improvements, a strong national <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> has been regarded as critical to national economic progress [<a href="#1" title="1">1</a>,<a href="#2" title="2">2</a>]. An efficient market, along with a sound financial system, makes it possible to not only support but also predict <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/economic-growth-53620.html'>economic growth</a> [<a href="#3" title="3">3</a>]. Capitalization, liquidity, asset pricing and turnover linked to <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> activities have all been used to determine whether or not a country's <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/economy-53220.html'>economy</a> is on solid ground [<a href="#4" title="4">4</a>]. Furthermore, economic expansion leads to the establishment of <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> markets, which allows for the prediction of future rates of capital, productivity and per capita Gross Domestic Product (GDP) growth [<a href="#5" title="5">5</a>,<a href="#6" title="6">6</a>].</p> <p>Because the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> is one of the most important fields in which investors invest, <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> price probably true is always a hot topic for academics in both the financial and technical fields. Financial time series prediction is notoriously difficult due to the widely accepted, semi-strong form of economic efficiency and the high amount of noise. Short-term <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price prediction was also done using <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/optimization-techniques-27488.html'>optimization techniques</a> like Principal Component Analysis (PCA) [<a href="#7" title="7">7</a>,<a href="#8" title="8">8</a>]. Over time, researchers have attempted to evaluate <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> transactions such as volume burst hazards, broadening the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> analysis study domain and indicating that this research domain still has a lot of promise [<a href="#9" title="9">9</a>]. Many proposed methods attempted to merge machine learning and deep learning techniques based on earlier approaches and then presented new metrics that serve as training features as <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/artificial-intelligence-47245.html'>artificial intelligence</a> techniques progressed in recent years [<a href="#10" title="10">10</a>]. This type of prior work is in the domain of feature engineering and can be used to inspire feature extension ideas in our research.</p> <p>To assess different quantitative methods in <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> markets, Convolutional Neural Network (CNN) as well as a Long Short-Term Memory (LSTM) neural network based models are mainly utilized [<a href="#11" title="11">11</a>]. The CNN is used for <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> selection and it automatically extracts features based on quantitative data and then uses an LSTM to retain time-series features in order to increase profits. In order to promote economic growth, the financial market is critical [<a href="#12" title="12">12</a>]. Individual investors and financial institutions can use financial time series data, such as stock market data, to move their investment toward beneficial returns [<a href="#13" title="13">13</a>]. Trading is as the act of buying and selling firm shares on a <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> exchange in order to maximise profits [<a href="#14" title="14">14</a>]. Making an informed trading decision without prior knowledge is analogous to playing golf while blindfolded. Every trader or individual needs a thorough understanding of market behaviour, company performance and knowledge of how and when to invest to make wise trading decisions [<a href="#15" title="15">15</a>].</p> <p>Every trader must choose the correct <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> to <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/trade-28644.html'>trade</a> in order to generate favourable profits. Aside from price and liquidity, volatility is an important factor to consider when choosing equities to <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/trade-28644.html'>trade</a> [<a href="#16" title="16">16</a>]. The upward and downward fluctuation of the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price is referred to as volatility. Stocks with higher volatility have a price that fluctuates considerably in either direction over a short period of time [<a href="#17" title="17">17</a>,<a href="#18" title="18">18</a>]. Stocks with low price volatility are less likely to rise or fall dramatically on any given day. Furthermore, various factors such as trading volume, news and financial reports, political events, economic conditions and investor expectations influence <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price [<a href="#19" title="19">19</a>,<a href="#20" title="20">20</a>]. High volatility equities are traditionally seen to be riskier, although swing traders frequently seek extremely volatile stocks in the hopes of generating better returns. The <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> value prediction process is illustrated in <strong>Figure 1</strong>.</p> <a onclick="openimage('https://www.longdom.org/articles-images-2023/Forex-Trading-price-10-4-249-g001.png','','scrollbars=yes,resizable=yes,width=500,height=330')" class="thumbnail"> <img src="https://www.longdom.org/articles-images-2023/Forex-Trading-price-10-4-249-g001.png" class="img-thumbnail img-fluid d-block mx-auto" alt="price" title="price" /> </a> <p><strong>Figure 1:</strong> Investor expectations influence <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price.</p> <p>There is no time gap between the arrival of information and its adjustment on <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price because the price adjustment is so quick. This rapid dissemination claim argues that there is no possibility to generate extra-nominal return with the knowledge available at a given time [<a href="#21" title="21">21</a>]. This result shows that an efficient market ensures a "fair game" in the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> return price mechanism. In other words, because all information available to market participants is included into its price, no investor is entitled to have any extra-nominal profit-generating information. In general, <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> prediction approaches can be divided into three categories: technical analysis, fundamental analysis and evolutionary analysis [<a href="#22" title="22">22</a>,<a href="#23" title="23">23</a>]. The most often used method is technical analysis, which is based on <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/statistical-analysis-4112.html'>statistical analysis</a> [<a href="#24" title="24">24</a>].</p> <p>The input data can be used to learn and analyse these statistics. However, numerous external factors influence the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> market trend, including the state of the corporation to which the shares belong, political order and global events [<a href="#25" title="25">25</a>]. As a result, stock market time series are frequently nonlinear and volatile. At the same time, there is a lot of volatility in the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> market. As a result, the data is quite noisy [<a href="#26" title="26">26</a>]. When developing a market forecast, it is critical to limit the risk to a minimum level. Deep learningbased techniques have recently demonstrated high accuracy in <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> data classification. For time series data analysis, Recurrent Neural Networks (RNNs) have been frequently employed [<a href="#27" title="27">27</a>].</p> <p>The goal of the time series <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> model is to map historical stock information. To assist with the next wave of <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> predictions, the historical data of stocks must be separated first. The first thing you should do with this method is collect and process data from time series [<a href="#28" title="28">28</a>]. Before projecting future trends in a time series, you must first observe the changes in its current trends and then determine future changes based on what you have learned about the past changes. When handling time series data, you are likely to encounter huge amounts of data, which are tedious to analyse [<a href="#29" title="29">29</a>]. This can be done by isolating the important trends and then separating the time series into separate parts. The initially complex data can be condensed while also reducing part of the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> sequence background noise with this division method. It is vital to not save information that is unhelpful for prediction because it allows the model to learn the variations in time series data more effectively and it makes it easier to find the time series rules.</p> <p>Many financial institutions have used <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/artificial-intelligence-47245.html'>Artificial Intelligence</a> (AI) approaches to predict <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> movements in recent decades. Deep learning has emerged as a dominating and popular AI technique in financial market analysis, with several promising outcomes in <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price predictions using nonlinear, data-driven and multivariate analysis [<a href="#30" title="30">30</a>]. In time series prediction, many deep <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/artificial-neural-networks-3057.html'>Artificial Neural Networks</a> (ANNs) have piqued researchers' interest. Fundamental and technical analysis is the two main techniques to making judgments in financial markets. Technical analysis derives technical indicators such as the Moving Average (MA), bollinger bands and logarithmic return from direct patterns in <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> data and visual elements of charts. Fundamental analysis, on the other hand, is the process of examining the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> at the most fundamental financial level in order to determine its intrinsic value. The vast majority of studies have concentrated on deep learning frameworks that rely on the raw dataset or a small number of characteristics. In order to deal with the complexities of the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> market, an efficient time series <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> predictions using time interval triggered flag attribute model using deep learning is proposed. As a result, technical indicators and macroeconomic variables are input into the system as a multivariate signal to estimate future <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> values of multiple companies.</p> <p>The <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> market's impact on a country's <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/economy-53220.html'>economy</a> goes far beyond simply mobilising capital. National <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/economic-growth-53620.html'>economic growth</a> is heavily dependent on a functioning national <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> because of the several critical services it provides, including capital accumulation and increased productivity. An effective banking system allows not just for economic growth, but also for economic forecasting. Various financial indicators, such as capitalization, liquidity, asset pricing and turnover, have been employed to determine whether a country's <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/economy-53220.html'>economy</a> is on solid ground or not. Investors are always interested in the movement of the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> market; therefore, predictions about price movements are important to both the financial and technical industries.</p> <p>TrevirNath, et al., [<a href="#1" title="1">1</a>] showed that, because of general market efficiency and significant noise, financial time series forecasting is difficult. Yaojun and Wang, et al., [<a href="#5" title="5">5</a>] employed artificial neural networks to forecast <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> prices and concentrated on volume, a specialised <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> attribute. They discovered that increasing the volume was not a useful way to improve forecasting results on the S and P 500 and DJI datasets. Han, et al., [<a href="#7" title="7">7</a>] used Support Vector Machine (SVM) models to short-term forecast <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> prices. SVM was more successful than Master Limited Partnership (MLP) in most cases and these findings were also dependent on the trading techniques. While the big data flood was rushing by, financial-domain researchers used established statistical and <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/signal-processing-26250.html'>signal processing</a> approaches to study <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> market data.</p> <p>The PCA optimization approaches were also used in the short-term prediction of <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> prices proposed by Qiu, et al., [<a href="#9" title="9">9</a>]. Researchers have long concentrated on analysing the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price, but more recently they have begun to look at the market's transaction history, which expands the realm of <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> research and indicates it has significant potential. It has been noted that in recent years, numerous <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/artificial-intelligence-47245.html'>artificial intelligence</a> solutions attempted to merge <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/machine-learning-31824.html'>machine learning</a> and deep learning techniques and that a novel metric used as a training feature had been proposed by Fischer, et al., [<a href="#11" title="11">11</a>].</p> <p>Pimenta, et al., [<a href="#16" title="16">16</a>] suggested a CNN and LSTM-based model to examine <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> quantitative methods. The CNN may be used to increase profits by choosing stocks based on quantitative data, automatically extracting time-series characteristics and applying an LSTM to save the features for use in the future. The financial sector is a critical component in supporting the economy. <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>Stock</a> exchange data analysis, which includes information on personal and institutional finances, <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/aids-113.html'>aids</a> investors and financial institutions in directing assets to promising sources of return. Trading, in our view, can be simply defined as the purchasing and selling of a company's shares on the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> exchange in order to maximise profit.</p> <p>To make effective trading judgments, users must be knowledgeable of market behaviour, company performance and know when and how to invest. Each trader must choose stocks intelligently in order to get profit. When it comes to selecting stocks to trade, liquidity and price are two important factors to consider, but volatility is the most important element. A fluctuation is the movement of the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price up or down. In the short term, equities with high volatility can move dramatically in either way. Because of the rapid price adjustment when information arrives, there is no delay between the arrival of news and its impact on <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price. A quick spread of this belief contends that information available at a certain time is impossible to exploit to obtain a non-normal return.</p> <p>External elements, such as the state of the firm and political order, have a significant impact on the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> market's movements. Since this is the case, time series in the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> are a nonlinear and dynamic process overall. At the same time, the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> market is experiencing quite a significant upheaval. As a result, the data is highly unreliable. To ensure a low risk, it is critical to conduct an accurate market forecast. New deep learning-based classification systems have shown that they have strong accuracy for <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> data classification. RNNs, especially, have been utilised in a variety of time series analyses. Shen, et al., [<a href="#18" title="18">18</a>] applied a deep convolutional neural network to short-term event-based <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> prediction.</p> <p>A feed forward network has multiple layers having an input layer is proposed by Zubair, et al., [<a href="#22" title="22">22</a>] having one or more hidden layers and an output layer. The inputs correspond to the measured properties of each training sample. Inputs are sent to the input layer at the same time. The weighted outputs of these units are simultaneously supplied to the next layer of units that comprise the hidden layer. The weighted outputs of the hidden layers serve as inputs to subsequent hidden layers and so on. The number of concealed layers is an arbitrary design challenge. The weighted output of the last hidden layer serves as input to the output layer, which forecasts the networks for specific samples.</p> <p>Back propagation is a learning algorithm for neural networks utilised by Thomas Fischer, et al., [<a href="#25" title="25">25</a>]. Back propagation networks learn by continually processing the sample set and contrasting the network prediction to the actual output. If the valuation exceeds the threshold, the weight of the interconnections is adjusted to lower the MSE between the prediction and original values. Weights are altered in the opposite way from the output layer to the first concealed layer. Back propagation is the name given to the technique since the modifications in the weights of the links are done in the opposite direction. To execute the calculations, use the back propagation procedure and compare the expected and target outputs. The anticipated value does not match the actual value; thus the weights are adjusted.</p> <p>Fische Mospel, et al., [<a href="#28" title="28">28</a>] proposed an ensemble deep ANNs for the purpose of Chinese <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> prediction. Deep belief networks, recurrent neural networks, LSTMs and reinforcement learning are also employed for predicting <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> prices. A Generative Adversarial Networks (GAN)-based <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> market prediction model is also proposed by Eunsuk Chong, et al., [<a href="#30" title="30">30</a>]. Contrary to popular belief, the primary means of evaluating stocks is simple financial analysis, which is used to gauge a stock's inherent value. Most previous researchers have concentrated on deep learning frameworks that employ the raw data or only a few features considered. Technical indications and macroeconomic variables are integrated into a multivariate signal and supplied to the system to help us understand where <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> prices will reach. <h4>Materials and Methods</h4> <p><strong>Proposed model</strong></p> <p>The ways to categorise stocks can be divided into numerous groups. Long-term investments are favoured by certain investors, while others prefer short-term investments. There are several signs of a <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price prediction that has no rules, the data is inconsistent and their models are incomplete. A typical one is a stock-related report that has average performance in <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price improvement.</p> <p>The primary subject of this research is short-term price trend forecasting for a specific time for several companies. Only the time series data is considered at this point, with no descriptive labels attached. The first thing performed here is to assign data categories. To identify trends in the price of a commodity, the current closing price relative to the closing price of the commodity in n days earlier is considered, where n is defined as 1 to 15, as our research is focused on the short term. In case the price trend is on the rise, the flag is triggered and marked as 1. Otherwise, labelled as 0. More specifically, the price movement for the n<sup>th</sup> day using the indices of the previous day's indices are analysed.</p> <p>The classification of valence was accomplished by the use of statistical parameters and CNN features, as illustrated in <strong>Figure 2</strong>. In the end, it was discovered that repeating the experiment produced greater performance of the classifier than using attribute values for a total of 240 samples in the first place. The input of the first CNN was consequently a 240 1 vector corresponding to around the first 2-3 layers. The convolution layers featured a one-dimensional Convolutional filter, Batch Normalisation (BN) and the max-pooling layer, which contained two-by-one filters in each of the two-by-one filters in the convolution layer. Each phase one convolution layer featured a total of 20 feature maps, enabling for cushioning of size one in each of the four convolution layers. To minimise over-fitting and boost performance, we applied a stabilised the input layer with <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> prediction data. Because there were 200 nodes in the dense layer (dense1) to construct the low-dimensional features after hidden layers, it is reasonable to assume that the initial CNN had 200 features.</p> <a onclick="openimage('https://www.longdom.org/articles-images-2023/Forex-Trading-Stages-10-4-249-g002.png','','scrollbars=yes,resizable=yes,width=500,height=330')" class="thumbnail"> <img src="https://www.longdom.org/articles-images-2023/Forex-Trading-Stages-10-4-249-g002.png" class="img-thumbnail img-fluid d-block mx-auto" alt="Stages" title="Stages" /> </a> <p><strong>Figure 2:</strong> Stages in Convolutional Neural Network (CNN) framework.</p> <p>The proposed model considers the dataset and then previous day fluctuations are calculated and the old value and new increased value set is maintained for every <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price prediction. The mean difference is calculated for the old value of <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> and increased value. The exponential moving average is calculated for average time fluctuations and exponential moving average is calculated. The relative strength index and stochastic oscillator flag is calculated for price prediction. The price rate of change of a stock is analysed for lower bound and upper bound prediction. The proposed model framework is represented in <strong>Figure 3</strong>.</p> <a onclick="openimage('https://www.longdom.org/articles-images-2023/Forex-Trading-exponential-10-4-249-g003.png','','scrollbars=yes,resizable=yes,width=500,height=330')" class="thumbnail"> <img src="https://www.longdom.org/articles-images-2023/Forex-Trading-exponential-10-4-249-g003.png" class="img-thumbnail img-fluid d-block mx-auto" alt="exponential" title="exponential" /> </a> <p><strong>Figure 3:</strong> The exponential moving average is calculated for average time.</p> <p>In time series data, Tg is considered as the time gap for fluctuations in the data and the Variables Set (VS) are considered and updated as</p> <p><img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e001.png" alt="Equation" /></p> <p>Where O1 is the old <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> value and U1 is the updated stock value in a Time gap (Tg) which has to trigger the model for stock price updation.</p> <p>The starting price of the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> of a specific organization in the starting of a day is predicted based on the previous day fluctuations and is calculated as</p> <p><img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e002.png" alt="Equation" /></p> <p>Where DSP is the day starting price, P is the previous day price, V is the difference between previous couple days, CP is the closing price, k is the threshold limit for increasing the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price, O1 is the old <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price and PL is the profit level on previous day.</p> <p>The Mean Difference (MD) of the previous day price and the starting day price of a specific organization is calculated as</p> <p><img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e003.png" alt="Equation" /></p> <p>Moving Average Convergence Divergence (MACD) is an indicator that shows the trend of the price and is based on Exponential Moving Average (EMA). MACD is calculated as</p> <p><em><img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e004.png" alt="Equation" /></em></p> <p>Here EMA signifies the more recent updated price and 7 and 14 represents the number of days’ values considered in the analysis of price prediction. Based on the MACD calculated, the EMA is updates as</p> <p><img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e005.png" alt="Equation" /></p> <p>Relative Strength Index (RSI) is an oscillator-based indicator that focuses on the strengths and weaknesses of the price. It is formulated as follows:</p> <p><img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e006.png" alt="Equation" /></p> <p>Williams Percentage (WP) is a technical indicator based on momentum. An investor can discover oversold and overbought circumstances using this indicator. The process of calculating WP is</p> <p><img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e007.png" alt="Equation" /></p> <p>Stochastic Oscillator Flag (SOF) is a composite measure that is based on the price's swiftness. As a general rule, momentum shifts occur before price shifts. According to a low-high range, it calculates the close price levels in real time. To calculate this Flag Attribute (FA) indicator, the process is</p> <p><em>SOF = DSP − PL +V</em></p> <p><img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e008.png" alt="Equation" /></p> <p>The flag attribute is triggered when there is a change in the stock price. The updating will be performed in a regular time intervals T1 and the updating are analysed for further predictions.</p> <p>Price Rate of Change (PROC) indicates the pace at which a price changes over a specific time period that is calculated as</p> <p><img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e009.png" alt="Equation" /></p> <p>The <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> prediction of any organization involves in calculating of lower bound and upper bound values in a day. The Lower Bound (LB) represents how lower the price will be on that day that is calculated as</p> <p><img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e010.png" alt="Equation" /></p> <p>Here λ represents the flag attribute fluctuations minimum count, Th is the threshold value added for the lower bound value of the day.</p> <p>The Upper Bound (UB) represents the maximum value a share can reach on a single day that is calculated based on the fluctuations flag attribute and the previous day closing value. The UB is calculated as</p> <p><img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e011.png" alt="Equation" /></p> <p>Here δ represents the flag attribute fluctuations maximum count, Th is the threshold value added for the lower bound value of the day. The error rate is measured as</p> <p><img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e012.png" alt="Equation" /> <h4>Results</h4> <p>The proposed model is implemented in python using Google Colab and the dataset is considered. The proposed Efficient Time Series <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>Stock Market</a> Predictions using Time Interval Triggered Flag Attribute model (ETSSMP-TITFA) is compared with the traditional Long Short-Term Memory (LSTM) Model. The proposed model is compared with the traditional model in terms of time series data clustering accuracy, fluctuations in price prediction accuracy levels, time series data classification time levels, lower bound prediction accuracy levels, upper bound prediction accuracy levels and market value prediction true positive rate. The results represent that the proposed model is better in its performance. The time series data clustering accuracy levels of the proposed and traditional models are represented in <strong>Figure 4</strong>.</p> <a onclick="openimage('https://www.longdom.org/articles-images-2023/Forex-Trading-series-10-4-249-g004.png','','scrollbars=yes,resizable=yes,width=500,height=330')" class="thumbnail"> <img src="https://www.longdom.org/articles-images-2023/Forex-Trading-series-10-4-249-g004.png" class="img-thumbnail img-fluid d-block mx-auto" alt="series" title="series" /> </a> <p><strong>Figure 4:</strong> Time series data clustering accuracy. <img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e013.png" alt="Equation" /> Time Series <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>Stock Market</a> Predictions using Time Interval Triggered Flag Attribute (ETSSMP-TITFA) model; <img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e014.png" alt="Equation" /> Memory (LSTM) model; MB: Monetary Base.</p> <p>Stock market prices are affected by demand-supply economics. In simple words, when demand for a <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> exceeds supply, there will be a rise in the price of a stock. The more drastic the demand-supply gap, the higher the price. The fluctuations in price prediction accuracy levels of the proposed and traditional model are represented in <strong>Figure 5</strong>. The results indicate that the proposed model prediction accuracy levels are high. The opening price of the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> considered is represented in <strong>Figure 6</strong>.</p> <a onclick="openimage('https://www.longdom.org/articles-images-2023/Forex-Trading-Opening-10-4-249-g005.png','','scrollbars=yes,resizable=yes,width=500,height=330')" class="thumbnail"> <img src="https://www.longdom.org/articles-images-2023/Forex-Trading-Opening-10-4-249-g005.png" class="img-thumbnail img-fluid d-block mx-auto" alt="Opening" title="Opening" /> </a> <p><strong>Figure 5:</strong> Opening price representation of a stock. <strong>Note:</strong> ZEEL: Zee <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/entertainment-10271.html'>Entertainment</a> Enterprises Limited.</p> <a onclick="openimage('https://www.longdom.org/articles-images-2023/Forex-Trading-Fluctuations-10-4-249-g006.png','','scrollbars=yes,resizable=yes,width=500,height=330')" class="thumbnail"> <img src="https://www.longdom.org/articles-images-2023/Forex-Trading-Fluctuations-10-4-249-g006.png" class="img-thumbnail img-fluid d-block mx-auto" alt="Fluctuations" title="Fluctuations" /> </a> <p><strong>Figure 6:</strong> Fluctuations in price prediction detection accuracy levels. <img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e015.png" alt="Equation" /> Efficient Time Series <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>Stock Market</a> Predictions using Time Interval Triggered Flag Attribute (ETSSMP-TITFA) model; <img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e016.png" alt="Equation" /> Long Short-Term Memory (LSTM) model; MB: Monetary Base.</p> <p>Organizations will have to determine their data and its level of sensitivity by defining a set of rules. Classifying data means to organise data into relevant categories in order to use and protect it better. The <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> representations in opening and upper and lower bounds are represented in <strong>Figure 7</strong>.</p> <a onclick="openimage('https://www.longdom.org/articles-images-2023/Forex-Trading-Representation-10-4-249-g007.png','','scrollbars=yes,resizable=yes,width=500,height=330')" class="thumbnail"> <img src="https://www.longdom.org/articles-images-2023/Forex-Trading-Representation-10-4-249-g007.png" class="img-thumbnail img-fluid d-block mx-auto" alt="Representation" title="Representation" /> </a> <p><strong>Figure 7:</strong> Representation of <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> value analysis.</p> <p>The time series data is a type of data that will be updated continuously and applying classification on such data is a critical task. The time series data classification time levels of the proposed and traditional models are indicated in <strong>Figure 8</strong>.</p> <a onclick="openimage('https://www.longdom.org/articles-images-2023/Forex-Trading-classification-10-4-249-g008.png','','scrollbars=yes,resizable=yes,width=500,height=330')" class="thumbnail"> <img src="https://www.longdom.org/articles-images-2023/Forex-Trading-classification-10-4-249-g008.png" class="img-thumbnail img-fluid d-block mx-auto" alt="classification" title="classification" /> </a> <p><strong>Figure 8:</strong> Time series data classification time levels. <img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e017.png" alt="Equation" /> Time Series <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>Stock Market</a> Predictions using Time Interval Triggered Flag Attribute (ETSSMP-TITFA) model; <img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e018.png" alt="Equation" /> Memory (LSTM) model; MB: Monetary Base. <h4>Discussion</h4> <p>The lower bound minimum possible price for a call option is defined as the variation between the current price of the stock and the option's current strike price. The value of the call option cannot drop below the current <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price minus the current dividend and strike price, as long as we are sure of the pay-out. The lower bound price prediction levels of the proposed and the traditional models are represented in <strong>Figure 9</strong>.</p> <a onclick="openimage('https://www.longdom.org/articles-images-2023/Forex-Trading-bound-10-4-249-g009.png','','scrollbars=yes,resizable=yes,width=500,height=330')" class="thumbnail"> <img src="https://www.longdom.org/articles-images-2023/Forex-Trading-bound-10-4-249-g009.png" class="img-thumbnail img-fluid d-block mx-auto" alt="bound" title="bound" /> </a> <p><strong>Figure 9:</strong> Lower bound prediction accuracy levels. <img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e019.png" alt="Equation" /> Short-Term Memory (LSTM) model; <img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e020.png" alt="Equation" /> Time Series Stock Market Predictions using Time Interval Triggered Flag Attribute (ETSSMP-TITFA) model; MB: Monetary Base.</p> <p>The upper bound is the smallest value that would round up to the next estimated value. The upper bound price prediction values of the proposed and the traditional models are represented in <strong>Figure 10</strong>. The results show that the proposed model upper bound prediction levels are accurate than the traditional models [<a href="#31" title="31">31</a>-<a href="#36" title="36">36</a>].</p> <a onclick="openimage('https://www.longdom.org/articles-images-2023/Forex-Trading-Upper-10-4-249-g010.png','','scrollbars=yes,resizable=yes,width=500,height=330')" class="thumbnail"> <img src="https://www.longdom.org/articles-images-2023/Forex-Trading-Upper-10-4-249-g010.png" class="img-thumbnail img-fluid d-block mx-auto" alt="Upper" title="Upper" /> </a> <p><strong>Figure 10:</strong> Upper bound prediction accuracy levels. <img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e021.png" alt="Equation" /> Efficient Time Series <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>Stock Market</a> Predictions using Time Interval Triggered Flag Attribute (ETSSMP-TITFA) model; <img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e022.png" alt="Equation" />Term Memory (LSTM) model; MB: Monetary Base.</p> <p>The <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> price prediction of the proposed model is represented in <strong>Figure 11</strong>. The predictions are accurate in the proposed model.</p> <a onclick="openimage('https://www.longdom.org/articles-images-2023/Forex-Trading-Stock-10-4-249-g011.png','','scrollbars=yes,resizable=yes,width=500,height=330')" class="thumbnail"> <img src="https://www.longdom.org/articles-images-2023/Forex-Trading-Stock-10-4-249-g011.png" class="img-thumbnail img-fluid d-block mx-auto" alt="Stock" title="Stock" /> </a> <p><strong>Figure 11:</strong> <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>Stock</a> market predictions. <img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e023.png" alt="Equation" /> <img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e024.png" alt="Equation" /></p> <p>Forecasting the price of an investment, such a <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> or bond, is all about trying to predict the future value of a company. Knowing in advance how a <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> will move will make you a lot of money. The proposed model performance level indicates that the stock market price prediction is more accurate when compared to traditional models. The price prediction accuracy levels of the proposed and traditional models are shown in <strong>Figure 12</strong>.</p> <a onclick="openimage('https://www.longdom.org/articles-images-2023/Forex-Trading-true-10-4-249-g012.png','','scrollbars=yes,resizable=yes,width=500,height=330')" class="thumbnail"> <img src="https://www.longdom.org/articles-images-2023/Forex-Trading-true-10-4-249-g012.png" class="img-thumbnail img-fluid d-block mx-auto" alt="true" title="true" /> </a> <p><strong>Figure 12:</strong> Market value prediction true positive rate. <img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e025.png" alt="Equation" /> Efficient Time Series <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>Stock Market</a> Predictions using Time Interval Triggered Flag Attribute (ETSSMP-TITFA) model; <img class="img-responsive" src="https://www.longdom.org/articles-images-2023/Forex-Trading-10-4-249-e026.png" alt="Equation" />Term Memory (LSTM) model.</p> <p>The <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> predictions based on the closing price is calculated and represented in <strong>Table 1</strong>. The proposed model prediction rate is accurate when compared to the traditional models.</p> <div class="table-responsive"> <table class="table table-striped"> <thead> <tr> <th>Date</th> <th>Adj close</th> <th>Predictions</th> </tr> </thead> <tbody> <tr> <td>24-09-2021</td> <td>320.65</td> <td>325.838837</td> </tr> <tr> <td>24-09-2021</td> <td>2.02</td> <td>1.214186</td> </tr> <tr> <td>27-09-2021</td> <td>317.74</td> <td>319.308044</td> </tr> <tr> <td>27-09-2021</td> <td>2</td> <td>0.155734</td> </tr> <tr> <td>28-09-2021</td> <td>312.67</td> <td>313.831665</td> </tr> <tr> <td>28-09-2021</td> <td>2.02</td> <td>1.068909</td> </tr> <tr> <td>29-09-2021</td> <td>309.93</td> <td>309.552124</td> </tr> <tr> <td>29-09-2021</td> <td>2.05</td> <td>1.010513</td> </tr> <tr> <td>30-09-2021</td> <td>304.79</td> <td>307.032562</td> </tr> <tr> <td>30-09-2021</td> <td>2.05</td> <td>2.482316</td> </tr> </tbody> </table> </div> <p><strong>Table 1:</strong> <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>Stock</a> market prediction rate. <h4>Conclusion</h4> <p>It has been difficult for computers to predict the <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> market since they need to do time series analysis. Deep neural networks have recently been used in numerous financial time series problems. Typically, it takes a lot of data samples to train a strong deep neural network. Despite this, the small sample size of stock market data has the unintended effect of making the networks more susceptible to over fitting. The main focus of this research is the short term prediction of <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> value for multiple companies based the factors considered using an efficient time series stock market predictions using time interval triggered flag attribute model using deep learning technique. As one of the stages in constructing the proposed predictive model, clustering gathers stocks with similar behaviour. At regular time intervals, the stock values are analysed and the flag attribute is triggered if change in <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price. The past <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> fluctuations are mainly considered and other parameters are also taken into account and then prediction will be performed. The proposed prediction model can aid traders in deciding which stocks to buy, increasing their trading range. It is observed that the proposed model findings improved when contrasted with the existing models. In future, the features considered can still be optimized and in less time the predictions need to be performed with improved accuracy levels.</p> <h4>References</h4> <ol> <li id='Reference_Title_Link' value='1'><a name="1" id='1'></a>Nath T. How big data has changed finance. Investopedia. 2015. <p>[<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=How+big+data+has+changed+finance.+Investopedia&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='2'><a name="2" id='2'></a>Saheli RC. <a href="https://finance.yahoo.com/news/machines-soon-able-learn-without-045000047.html">Machines will soon will be able to learn without being programmed. 2018</a>. <p>[<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=Machines+will+soon+will+be+able+to+learn+without+being+programmed&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='3'><a name="3" id='3'></a>Verma R, Choure P, Singh U. <a href="https://ieeexplore.ieee.org/abstract/document/8212717">Neural networks through <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> data prediction</a>. Int Conf Electron Inf Commun. 2017;2:514-519. <a href="https://doi.org/10.1109/ICECA.2017.8212717">[Crossref</a>] <p>[<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=3.%09Verma+R%2C+Choure+P%2C+Singh+U.+Neural+networks+through+stock+market+data+prediction&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='4'><a name="4" id='4'></a>Pushkar K, Shree RS. <a href="http://conference.ioe.edu.np/publications/ioegc2016/IOEGC-2016-45.pdf">Analysis and Prediction of <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>Stock</a> Prices of Nepal using different <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/machine-learning-31824.html'>Machine Learning</a> Algorithms</a>. 2016;337-339.</li> <li id='Reference_Title_Link' value='5'><a name="5" id='5'></a>Wang Y, Wang Y. <a href="https://ieeexplore.ieee.org/abstract/document/7509794">Using social media mining technology to assist in price prediction of <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> market</a>. Int Conf Big Data Smart Comput. 2016;1-4. <p>[<a href="https://doi.org/10.1109/ICBDA.2016.7509794">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=Using+social+media+mining+technology+to+assist+in+price+prediction+of+stock+market&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='6'><a name="6" id='6'></a>Sharma A, Bhuriya D, Singh U. <a href="https://ieeexplore.ieee.org/abstract/document/8212715">Survey of <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> prediction using <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/machine-learning-31824.html'>machine learning</a> approach</a>. Int. Conf Electron Inf Commun. 2017;2:506-509. <p>[<a href="https://doi.org/10.1109/ICECA.2017.8212715">Crossref</a>] <a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=Survey+of+stock+market+prediction+using+machine+learning+approach&btnG=">[Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='7'><a name="7" id='7'></a>Kim KJ, Han I. <a href="https://www.sciencedirect.com/science/article/abs/pii/S0957417400000270">Genetic algorithms approach to feature discretization in <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/artificial-neural-networks-3057.html'>artificial neural networks</a> for the prediction of <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price index</a>. Expert Syst Appl. 2000;19(2):125-132. <p>[<a href="https://doi.org/10.1016/S0957-4174(00)00027-0">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=7.%09Kim+K%2C+Han+I.+Genetic+algorithms+approach+to+feature+discretization+in+artificial+neural+networks+for+the+prediction+of+stock+price+index.+Expert+Syst+Appl.+2000%3B19%3A125%E2%80%9332.+https%3A%2F%2Fdoi.org%2F10.1016%2FS0957-4174%2800%2900027-0&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='8'><a name="8" id='8'></a>Piramuthu S. <a href="https://www.sciencedirect.com/science/article/abs/pii/S0377221702009116">Evaluating feature selection methods for learning in <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/data-mining-3995.html'>data mining</a> applications</a>. Eur J Oper Res. 2004; 156(2):483-494. <p>[<a href="https://doi.org/10.1016/S0377-2217(02)00911-6">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=8.%09Piramuthu+S.+Evaluating+feature+selection+methods+for+learning+in+data+mining+applications.+Eur+J+Oper+Res.+2004%3B156%282%29%3A483%E2%80%9394.+https%3A%2F%2Fdoi.org%2F10.1016%2FS0377-2217%2802%2900911-6.+&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='9'><a name="9" id='9'></a>Qiu M, Song Y. <a href="https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0155133">Predicting the direction of <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> index movement using an optimized artificial neural network model</a>. PloS one. 2016;11(5):e0155133. <p>[<a href="https://doi.org/10.1371/journal.pone.0155133">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=9.%09Qiu+M%2C+Song+Y.+Predicting+the+direction+of+stock+market+index+movement+using+an+optimized+artificial+neural+network+model.+PLoS+ONE.+2016%3B11%285%29%3Ae0155133&btnG=">Google Scholar</a>] [<a href="https://pubmed.ncbi.nlm.nih.gov/27196055/">PubMed</a>]</p> </li> <li id='Reference_Title_Link' value='10'><a name="10" id='10'></a>Hassan MR, Nath B. <a href="https://ieeexplore.ieee.org/abstract/document/1578783">Stock market forecasting using hidden Markov model: a new approach</a>. Conference on Intelligent Systems Design and Applications. 2005;2005:192-196. <p>[<a href="https://doi.org/10.1109/ISDA.2005.85">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=Stock+market+forecasting+using+hidden+Markov+model%3A+a+new+approach&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='11'><a name="11" id='11'></a>Fischer T, Krauss C. <a href="https://www.sciencedirect.com/science/article/abs/pii/S0377221717310652">Deep learning with long short-term memory networks for financial market predictions</a>. Eur J Oper Res. 2018;270(2):654-669. <p>[<a href="https://doi.org/10.1016/j.ejor.2017.11.054">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=Deep+learning+with+long+short-term+memory+networks+for+financial+market+predictions&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='12'><a name="12" id='12'></a>Hafezi R, Shahrabi J, Hadavandi E. <a href="https://www.sciencedirect.com/science/article/abs/pii/S1568494614006723">A bat-neural network multi-agent system (BNNMAS) for <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price prediction: Case study of DAX <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> price</a>. Appl Soft Comput. 2015;29:196-210. <p>[<a href="https://doi.org/10.1016/j.asoc.2014.12.028">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=12.%09Hafezi+R%2C+Shahrabi+J%2C+Hadavandi+E.+A+bat-neural+network+multi-agent+system+%28BNNMAS%29+for+stock+price+prediction%3A+case+study+of+DAX+stock+price.+Appl+Soft+Comput+J.+2015%3B29%3A196%E2%80%93210.+https%3A%2F%2Fdoi.org%2F10.1016%2Fj.asoc.2014.12.028&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='13'><a name="13" id='13'></a>McNally S, Roche J, Caton S. <a href="https://ieeexplore.ieee.org/abstract/document/8374483">Predicting the price of bitcoin using machine learning</a>. International Conference on Parallel, Distributed and Network-Based Processing. 2018;339-343. <p>[<a href="https://doi.org/10.1109/PDP2018.2018.00060">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=Predicting+the+price+of+bitcoin+using+machine+learning&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='14'><a name="14" id='14'></a>Nagar A, Hahsler M. <a href="http://past.rinfinance.com/agenda/2012/talk/Nagar%2BHahsler.pdf">News sentiment analysis using R to predict <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> trends</a>. 2012. <p>[<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=14.%09Nagar+A%2C+Hahsler+M.+News+sentiment+analysis+using+R+to+predict+stock+market+trends.+2012.+http%3A%2F%2Fpast.rinfinance.com%2Fagenda%2F2012%2Ftalk%2FNagar%2BHahsler.pdf.+Accessed+20+July+2019.+&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='15'><a name="15" id='15'></a>Nekoei Qachkanloo H, Ghojogh B, Pasand AS, Crowley M. <a href="https://ojs.aaai.org/index.php/AAAI/article/view/5016">Artificial counselor system for <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> investment</a>. IAAI Technical Track: Emerging Papers. 2019;33(1):9558-9564. <p>[<a href="https://doi.org/10.1609/aaai.v33i01.33019558">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=15.%09Nekoeiqachkanloo+H%2C+Ghojogh+B%2C+Pasand+AS%2C+Crowley+M.+Artificial+counselor+system+for+stock+investment.+2019.+ArXiv+Preprint+arXiv%3A1903.00955&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='16'><a name="16" id='16'></a>Pimenta A, Nametala CA, Guimarães FG, Carrano EG. <a href="https://link.springer.com/article/10.1007/s10614-017-9665-9">An automated investing method for <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> based on multiobjective genetic programming</a>. Comput Econ. 2018;52(1):125-144. <p>[<a href="https://doi.org/10.1007/s10614-017-9665-9">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=16.%09Pimenta+A%2C+Nametala+CAL%2C+Guimar%C3%A3es+FG%2C+Carrano+EG.+An+automated+investing+method+for+stock+market+based+on+multiobjective+genetic+programming.+Comput+Econ.+2018%3B52%281%29%3A125%E2%80%9344.+https%3A%2F%2Fdoi.org%2F10.1007%2Fs10614-017-9665-9.+&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='17'><a name="17" id='17'></a>Shen J. <a href="https://repository.library.carleton.ca/concern/etds/d504rm29s">Short-term <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>Stock Market</a> Price Trend Prediction Using a Customized Deep Learning System</a>. J Big Data. 2020;7(1):66. <p>[<a href="https://doi.org/10.22215/etd/2019-13721">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=Short-term+Stock+Market+Price+Trend+Prediction+Using+a+Customized+Deep+Learning+System&btnG=">Google Scholar</a>] [<a href="https://pubmed.ncbi.nlm.nih.gov/32923309/">PubMed</a>]</p> </li> <li id='Reference_Title_Link' value='18'><a name="18" id='18'></a>Shen J, Shafiq MO. <a href="https://ieeexplore.ieee.org/abstract/document/8614117">Deep learning convolutional neural networks with dropout-a parallel approach</a>. Int. J. Mach. Learn. Comput. 2018;572-577. <p>[<a href="https://doi.org/10.1109/ICMLA.2018.00092">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=Deep+learning+convolutional+neural+networks+with+dropout-a+parallel+approach&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='19'><a name="19" id='19'></a>Sirignano J, Cont R. <a href="https://www.tandfonline.com/doi/abs/10.1080/14697688.2019.1622295">Universal features of price formation in financial markets: perspectives from deep learning</a>. Quant Finance. 2019;19(9):1449-1459. <p>[<a href="https://doi.org/10.1080/14697688.2019.1622295">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=19.%09Sirignano+J%2C+Cont+R.+Universal+features+of+price+formation+in+financial+markets%3A+perspectives+from+deep+learning.+Ssrn.+2018&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='20'><a name="20" id='20'></a>Thakur M, Kumar D. <a href="https://www.sciencedirect.com/science/article/abs/pii/S1568494618301224">A hybrid financial trading support system using multi-category classifiers and random forest</a>. Appl Soft Comput. 2018;67:337-349. <p>[<a href="https://doi.org/10.1016/j.asoc.2018.03.006">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=20.%09Thakur+M%2C+Kumar+D.+A+hybrid+financial+trading+support+system+using+multi-category+classifiers+and+random+forest.+Appl+Soft+Comput+J.+2018%3B67%3A337%E2%80%9349.+https%3A%2F%2Fdoi.org%2F10.1016%2Fj.asoc.2018.03.006.+&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='21'><a name="21" id='21'></a>Weng B, Lu L, Wang X, Megahed FM, Martinez W. <a href="https://www.sciencedirect.com/science/article/abs/pii/S0957417418303622">Predicting short-term <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> prices using ensemble methods and online data sources</a>. Expert Syst Appl. 2018;112:258-273. <p>[<a href="https://doi.org/10.1016/j.eswa.2018.06.016">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=21.%09Weng+B%2C+Lu+L%2C+Wang+X%2C+Megahed+FM%2C+Martinez+W.+Predicting+short-term+stock+prices+using+ensemble+methods+and+online+data+sources.+Expert+Syst+Appl.+2018%3B112%3A258%E2%80%9373.+https%3A%2F%2Fdoi.org%2F10.1016%2Fj.eswa.2018.06.016.&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='22'><a name="22" id='22'></a>Asghar MZ, Rahman F, Kundi FM, Ahmad S. <a href="https://link.springer.com/article/10.1007/s10588-019-09292-7">Development of <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> trend prediction system using multiple regression</a>. Comput Math Organ Theory. 2019;25(3):271-301. <p>[<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=Development+of+stock+market+trend+prediction+system+using+multiple+regression&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='23'><a name="23" id='23'></a>Lee TK, Cho JH, Kwon DS, Sohn SY. <a href="https://www.sciencedirect.com/science/article/abs/pii/S0957417418305761">Global <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> investment strategies based on financial network indicators using <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/machine-learning-31824.html'>machine learning</a> techniques</a>. Expert Syst Appl. 2019;117:228-242. <p>[<a href="https://doi.org/10.1016/j.eswa.2018.09.005">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=23.%09Tae+Kyun+Lee+et+al.+%E2%80%9CGlobal+stock+market+investment+strategies+based+on+financial+network+indicators+using+machine+learning+tech+niques%E2%80%9D%2C+Expert+Systems+with+Applications%2C+117%282019%29%3A228-242.&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='24'><a name="24" id='24'></a>Henrique BM, Sobreiro VA, Kimura H. <a href="https://www.sciencedirect.com/science/article/abs/pii/S095741741930017X">Literature review: Machine learning techniques applied to financial market prediction</a>. Expert Syst Appl. 2019;124:226-251. <p>[<a href="https://doi.org/10.1016/j.eswa.2019.01.012">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=24.%09Bruno+et+al.+%E2%80%9CLiterature+review%3A+Machine+learning+techniques+applied+to+financial+market+prediction%E2%80%9D%2C+Expert+Systems+with+Applications%2C+124%282019%29%3A+226-251.+&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='25'><a name="25" id='25'></a>Fischer T, Krauss C. <a href="https://www.sciencedirect.com/science/article/abs/pii/S0377221717310652">Deep learning with long short-term memory networks for financial market predictions</a>. Eur J Oper Res. 2018;270(2):654-669. <p>[<a href="https://doi.org/10.1016/j.ejor.2017.11.054">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=25.%09Thomas+Fischer+et+al.+%E2%80%9CDeep+learning+with+long+short-term+memory+networks+for+financial+market+predictions%E2%80%9D%2C+European+Journal+of+Operational+Research%2C+270.2%282018%29%3A+654-669.&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='26'><a name="26" id='26'></a>Zhang K, Zhong G, Dong J, Wang S, Wang Y. <a href="https://www.sciencedirect.com/science/article/pii/S1877050919302789">Stock market prediction based on generative adversarial network</a>. Procedia Comput Sci. 2019;147:400-406. <p>[<a href="https://doi.org/10.1016/j.procs.2019.01.256">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=26.%09Kang+Zhang+et+al.+%E2%80%9CStock+Market+Prediction+Based+on+Generative+Adversarial+Network%E2%80%9D%2C+Procardia+Computer+Science%2C+147%282019%29%3A400-406.+&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='27'><a name="27" id='27'></a>Moews B, Herrmann JM, Ibikunle G. <a href="https://www.sciencedirect.com/science/article/abs/pii/S0957417418307474">Lagged correlation-based deep learning for directional trend change prediction in financial time series</a>. Expert Syst Appl. 2019;120:197-206. <p>[<a href="https://doi.org/10.1016/j.eswa.2018.11.027">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=27.%09Ben+Moews+et+at.+">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='28'><a name="28" id='28'></a>Mospel F. Deep learning with machine learning algorithms for financial market predictions. Eur J Res. 2019;220(2):654-669. <p>[<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=Deep+learning+with+machine+learning+algorithms+for+financial+market+predictions&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='29'><a name="29" id='29'></a>Karhunen M. <a href="https://www.sciencedirect.com/science/article/abs/pii/S0957417418304871">Algorithmic sign prediction and covariate selection across eleven international <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> markets</a>. Expert Syst Appl. 2019;115:256-263. <p>[<a href="https://doi.org/10.1016/j.eswa.2018.07.061">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=29.%09MarkkuKarhunen+et+al.+%E2%80%9CAlgorithmic+sign+prediction+and+covariate+selection+across+eleven+international+stock+markets%E2%80%9D%2C+Expert+Systems+with+Applications%2C+115%282019%29%3A256-263.++&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='30'><a name="30" id='30'></a>Chong E, Han C, Park FC. <a href="https://www.sciencedirect.com/science/article/abs/pii/S0957417417302750">Deep learning networks for <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> analysis and prediction: Methodology, data representations, and case studies</a>. Expert Syst Appl. 2017;83:187-205. <p>[<a href="https://doi.org/10.1016/j.eswa.2017.04.030">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=30.%09Eunsuk+Chong+et+at.+%E2%80%9CDeep+learning+networks+for+stock+market+analysis+and+prediction%3A+Methodology%2C+data+representations%2C+and+case+studies%E2%80%9D%2C+Expert+Systems+with+Applications%2C8+%282017%29%3A+187-205.&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='31'><a name="31" id='31'></a>Wang Q, Xu W, Zheng H. <a href="https://www.sciencedirect.com/science/article/abs/pii/S0925231218303540">Combining the wisdom of crowds and technical analysis for financial market prediction using deep random subspace ensembles</a>. Neurocomputing. 2018;299:51-61. <p>[<a href="https://doi.org/10.1016/j.neucom.2018.02.095">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=31.%09WangQili+et+al.+%E2%80%9CCombining+the+wisdom+of+crowds+and+technical+analysis+for+financial+market+prediction+using+deep+random+subspace+ensembles%E2%80%9D%2C+Neurocomputing%2C+299%282018%29%3A51-61.++&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='32'><a name="32" id='32'></a>Lee C, Ku S, Cho P, Chang W. <a href="https://www.sciencedirect.com/science/article/abs/pii/S0378437119303103">Explaining future market return and evaluating market condition with common preferred spread index</a>. Phys. A: Stat Mech Appl. 2019;525:921-934. <p>[<a href="https://doi.org/10.1016/j.physa.2019.03.075">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=32.%09ChangjuLee+et+al.+%E2%80%9CExplaining+future+market+return+and+evaluating+market+condition+with+common+preferred+spread+index%E2%80%9D%2C+Physica+A%3A+Statistical+Mechanics+and+its+Applications%2C+220%282019%29%3A220-229.++&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='33'><a name="33" id='33'></a>Chen MY, Liao CH, Hsieh RP. <a href="https://www.sciencedirect.com/science/article/abs/pii/S074756321930113X">Modeling public mood and emotion: <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>Stock</a> market trend prediction with anticipatory computing approach</a>. Comput Hum Behav. 2019;101:402-408. <p>[<a href="https://doi.org/10.1016/j.chb.2019.03.021">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=33.%09Mu-YenChen+et+al.+%E2%80%9CModeling+public+mood+and+emotion%3A+Stock+market+trend+prediction+with+anticipatory+computing+approach%E2%80%9D%2C+Computers+in+Human+Behavior+%282018%29.++&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='34'><a name="34" id='34'></a>Hiransha M, Gopalakrishnan EA, Menon VK, Soman KP. <a href="https://www.sciencedirect.com/science/article/pii/S1877050918307828">NSE <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-market-56074.html'>stock market</a> prediction using deep-learning models</a>. Procedia Comput Sci. 2018;132:1351-1362. <p>[<a href="https://doi.org/10.1016/j.procs.2018.05.050">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=NSE+Stock+Market+Prediction+Using+Deep-Learning+Models&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='35'><a name="35" id='35'></a>Yang F, Chen Z, Li J, Tang L. <a href="https://www.sciencedirect.com/science/article/abs/pii/S1568494619301462">A novel hybrid <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> selection method with <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/stock-6023.html'>stock</a> prediction</a>. Appl Soft Comput. 2019;80:820-831. <p>[<a href="https://doi.org/10.1016/j.asoc.2019.03.028">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=35.%09FengmeiYang+et+al.+%E2%80%9CA+novel+hybrid+stock+selection+method+with+stock+prediction%E2%80%9D%2C+Applied+Soft+Computing+%282019%29.&btnG=">Google Scholar</a>]</p> </li> <li id='Reference_Title_Link' value='36'><a name="36" id='36'></a>Song YG, Cao QL, Zhang C. <a href="https://www.sciencedirect.com/science/article/abs/pii/S1389041718304376">Towards a new approach to predict <a target='_blank' href='https://www.longdom.org/peer-reviewed-journals/business-12012.html'>business</a> performance using machine learning</a>. Cogn Syst Res. 2018;52:1004-1012. <p>[<a href="https://doi.org/10.1016/j.cogsys.2018.09.006">Crossref</a>] [<a href="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=36.%09Yue-gang+Song+et+al.Corrigendum+to+%E2%80%9CTowards+a+new+approach+to+predict+business+performance+using+machine+learning%E2%80%9D+%5BCogn.+Syst.+Res.+52+%282018%29%3A+1004-1012%5D.+&btnG=">Google Scholar</a>]</p> </li> </ol>   <div class="card bg-light mb-3"> <div class="card-body px-3 pb-0"> <h4 class="font-size-4"><a id="ai"></a>Author Info</h4> <a href='https://www.longdom.org/author/sudhakar-kalva-67001' title='Sudhakar Kalva' style='color:#555; border-bottom:1px dotted #CCC;'>Sudhakar Kalva</a><sup><a href='#a1'>1</a></sup><sup><a href='#Sudhakar_Kalva'>*</a></sup> and <a href='https://www.longdom.org/author/naganjaneyulu-satuluri-67003' title='Naganjaneyulu Satuluri' style='color:#555; border-bottom:1px dotted #CCC;'>Naganjaneyulu Satuluri</a><sup><a href='#a2'>2</a></sup> <div> </div> <a id="a1"></a><sup>1</sup>Department of Computer Science and Engineering, Jawaharlal Nehru Technological University, Kakinada, Andhra Pradesh, India<br> <a id="a2"></a><sup>2</sup>Department of Information Technology, LakiReddy Bali Reddy College of Engineering, Mylavaram, Andhra Pradesh, India<br> <div> </div> <p><strong>Citation:</strong> Kalva S, Satuluri N (2024) Time Series Stock Market Predictions: Using Time Interval Triggered of Flag Attribute Model in Deep Learning. J Stock Forex. 11:249</p> <p> <strong>Received: </strong>20-Dec-2022, Manuscript No. JSFT-22-21026; <strong>Editor assigned: </strong>26-Dec-2022, Pre QC No. JSFT-22-21026 (PQ); <strong>Reviewed: </strong>09-Jan-2023, QC No. JSFT-22-21026; <strong>Revised: </strong>16-Jan-2023, Manuscript No. JSFT-22-21026 (R); <strong>Published:</strong> 01-Mar-2024 , DOI: 10.35248/2168-9458.24.11.249</p> <p><strong>Copyright: </strong>漏 2024 Kalva S, et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.</p> </div> </div> </div> </div> </div> </section> <footer class="bg-blue-grey-900 py-3"> <div class="container"> <div class="row"> <div class="col-12 col-sm-4"> <h4 class="white font-size-4 fweight-400 border-bottom-1 pb-2">Content Links</h4> <ul class="list-unstyled footer-links font-size-3"> <li><a class="" href="https://www.longdom.org/online-tools.html" title="Click here">Tools</a> </li> <li><a class="" href="https://www.longdom.org/feedback.html" title="Click here">Feedback</a></li> <li><a class="" href="https://www.longdom.org/careers.html" title="Click here">Careers</a></li> <li><a class="" href="https://www.longdom.org/privacy-policy.html" title="Click here">Privacy Policy</a></li> <li><a class="" href="https://www.longdom.org/terms-conditions.html" title="Click here">Terms & Conditions</a></li> <li><a class="" href="https://www.longdom.org/authors-reviewers-editors.html" title="Click here">Authors, Reviewers & Editors</a></li> </ul> </div> <div class="col-12 col-sm-4"> <h4 class="white font-size-4 fweight-400 border-bottom-1 pb-2">Contact Longdom</h4> <p>Longdom Group SA<br> Avenue Roger Vandendriessche,<br> 18, 1150 Brussels, Belgium<br> Phone: +442038085340 <br><strong>Email:</strong> <a href="mailto:info@longdom.org" class="white" title="Click here">info@longdom.org</a></p> </div> <div class="col-12 col-sm-4"> <h4 class="white font-size-4 fweight-400 border-bottom-1 pb-2">Connect</h4> <nav class="nav nav-pills social-icons-footer flex-column a-pl-0"> <a href="https://www.facebook.com/longdompublisher" title="Click here" target="_blank" class="nav-link bg-facebook-hover"><i class="fab fa-facebook-f bg-facebook"></i> Facebook</a> <a href="https://www.linkedin.com/company/longdom-publishing-sl/" title="Click here" target="_blank" class="nav-link bg-linkedin-hover"><i class="fab fa-linkedin-in bg-linkedin"></i> Linkedin</a> <a href="https://twitter.com/LongdomP" title="Click here" target="_blank" class="nav-link bg-twitter-hover"><i class="fab fa-twitter bg-twitter"></i> Twitter</a> <a href="https://www.instagram.com/longdom_publisher/" title="Click here" target="_blank" class="nav-link bg-instagram-hover"><i class="fab fa-instagram bg-instagram"></i> Instagram</a> </nav> </div> </div> <div class="row text-center"> <div class="col"> <p>Copyright © 2024 <a href="https://www.longdom.org/" title="Click here" class="white">Longdom Publishing</a>.</p> </div> </div> </div> </footer>  <a href="#0" class="cd-top js-cd-top">Top</a>   <script defer src="https://code.jquery.com/jquery-3.3.1.min.js"></script> <script defer src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.7/umd/popper.min.js"></script> <script defer src="https://stackpath.bootstrapcdn.com/bootstrap/4.3.1/js/bootstrap.min.js"></script>  <script> jQuery(function($) { $(window).scroll(function fix_element() { $('#target').css( $(window).scrollTop() > 100 ? { 'position': 'fixed', 'top': '440px' } : { 'position': 'absolute', 'top': '440px' } ); return fix_element; }()); }); </script>   <script defer src="https://unpkg.com/feather-icons"></script> <script> feather.replace() </script>  <script defer src="/assets/js/scroll-to-top.js"></script>  <script defer type="text/javascript" src="/assets/js/coolautosuggest.js"></script> <script language="javascript" type="text/javascript"> $("#keyword").coolautosuggest({ url: "https://www.longdom.org/author-names.php?chars=", minChars: 3, }); </script> <script defer src="/assets/js/jquery.mCustomScrollbar.concat.min.js"></script> <script> // Scrollbar var Scrollbar = function() { "use strict"; // Handle Scrollbar Linear var handleScrollbarLinear = function() { $(".scrollbar").mCustomScrollbar({ theme: "minimal-dark" }); } return { init: function() { handleScrollbarLinear(); // initial setup for scrollbar linear } } }(); $(document).ready(function() { Scrollbar.init(); }); /*========================== Stikcy Navbar ============================*/ window.onscroll = function() { myFunction() }; var navbar = document.getElementById("sticky-navbar"); var sticky = navbar.offsetTop; function myFunction() { if (window.pageYOffset >= sticky) { navbar.classList.add("sticky") } else { navbar.classList.remove("sticky"); } } /*========================== Bootstrap Popover ============================*/ $(function () { $('[data-toggle="popover"]').popover() }) </script>  <script defer src="/assets/js/jquery.malihu.PageScroll2id.min.js"></script> <script> (function($){ $(window).on("load",function(){ $("a[rel='m_PageScroll2id']").mPageScroll2id(); }); })(jQuery); </script>  <script defer type="text/javascript" src="/assets/js/jquery.matchHeight-min.js"></script> <script> $(function() { $('.match-height').matchHeight({ byRow: true, property: 'height', target: null, }); }); </script> <script defer type="text/javascript" src="/assets/js/grids.min.js"></script> <script type="text/javascript"> // Equal Height var EqualHeight = function() { "use strict"; // Handle Equal Height var handleEqualHeight = function() { $(function($) { $('.equal-height').responsiveEqualHeightGrid(); }); } return { init: function() { handleEqualHeight(); // initial setup for equal height } } }(); $(document).ready(function() { EqualHeight.init(); }); </script>  <script defer src="https://cdnjs.cloudflare.com/ajax/libs/bootstrap-select/1.13.2/js/bootstrap-select.min.js"></script> <script> $('.selectpicker').selectpicker(); </script> <script> $(document).ready(function(){ var filecount = 1; $('.filerowclass').each(function(){ var countattr = $(this).attr('countattr'); if(filecount == countattr){ var countlink = $('#rowfile'+countattr+ ' .filelinkclass').length; if(countlink == 0){ $('#rowfile'+countattr).remove(); } } filecount++; }); }); </script>  <script type="text/javascript"> $(document).ready(function() { $("#wait").hide(); $("#jkeyword").keyup(function() { $("#wait").show(); //values of sending variables var jkeyword=$("#jkeyword").val(); var dataString = { 'jkeyword':jkeyword }; $.ajax ({ type: "POST", url: "https://www.longdom.org/journal-search.php", data: dataString, cache: false, success: function(html) { $("#jresult").html(html); $("#wait").hide(); } }); }); }); </script> <link href="https://cdn.jsdelivr.net/npm/select2@4.1.0-rc.0/dist/css/select2.min.css" rel="stylesheet" /> <script defer src="https://cdn.jsdelivr.net/npm/select2@4.1.0-rc.0/dist/js/select2.min.js"></script> </body> </html>