<?xml version="1.0" encoding="UTF-8"?> <rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:sy="http://purl.org/rss/1.0/modules/syndication/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"> <channel> <title>International Journal of Supply and Operations Management</title> <link>http://www.ijsom.com/</link> <description>International Journal of Supply and Operations Management</description> <atom:link href="" rel="self" type="application/rss+xml"/> <language>en</language> <sy:updatePeriod>daily</sy:updatePeriod> <sy:updateFrequency>1</sy:updateFrequency> <pubDate>Fri, 01 Nov 2024 00:00:00 +0330</pubDate> <lastBuildDate>Fri, 01 Nov 2024 00:00:00 +0330</lastBuildDate> <item> <title>Multivariate Sales Forecasting Using Gated Recurrent Unit Network Model</title> <link>http://www.ijsom.com/article_2944.html</link> <description>Market forecasting is an integral part of supply chain management. Machine learning models have turned a new page in predictive analysis and helped organizations achieve improved accuracy. This paper focuses on creating a Gated Recurrent Unit (GRU) model to predict sales for multiple stores as a multivariate time series. GRUs are a variation of Recurrent Neural Networks (RNNs) used to sequence modelling tasks. The dataset used to create the model contains the unit sales of 3,049 SKUs sold in 10 stores. The sales data from the 3049 SKUs were grouped into the 7 departments to use as input to the model. A Vector Autoregression (VAR) and LightGBM models were used to compare the GRU model predictions. Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) were used to compare the 2 models. The mean MAPE values for forecasts of the GRU, VAR, and LightGBM models were 13.77%, 14.87%, and 14.24% respectively, while MAE values were 68 Units, 72 Units, and 69 Units Respectively. The study reveals that the GRU model provides more accuracy for multivariate sales forecasting due to its ability to learn hidden patterns automatically and handle time mechanisms such as trends and seasonality.</description> </item> <item> <title>A CNN鈥揕STM Hybrid Deep Learning Model for Detergent Products Demand Forecasting: A Case Study</title> <link>http://www.ijsom.com/article_2943.html</link> <description>An accurate forecast of current and future demand is an essential initial step for almost all the facets of supply chain optimization, including inventory strategy, production scheduling, distribution management, and marketing policies. Simply put, a more accurate demand prediction can lead to a more optimized supply chain process, allowing for better inventory control and higher customer satisfaction. Classical demand predictions are based principally on qualitative approaches relying on data from experts' opinions; quantitative forecasts based on historical data through statistical and artificial neural network models or a mix of qualitative and quantitative techniques that is also widely used and has shown good performances. Detergents and cleaning products demand is extremely volatile and has undergone substantial change, especially during the COVID-19 health crisis. In this paper, we present a hybrid Neural Network approach for accurate demand forecasts of the detergent manufacturing industry. It mainly consists of the combination of Long Short-Term Memory (LSTM) with Convolution Neural Network (CNN) based approaches. We performed a series of experiments on real data sets and assessed the performance of the proposed CNN&amp;amp;ndash;LSTM hybrid model. Numerical results showed that the combination of LSTM layers with complementary CNN layers provides more accurate results than other state-of-the-art forecasting models.</description> </item> <item> <title>Evaluate The Role of Policies in The Sustainability of the Supply Chain Through a Comprehensive Mathematical Approach</title> <link>http://www.ijsom.com/article_2942.html</link> <description>This study has two policies to support supply chains. In the first model, three types of subsidies are provided for each supplier. In the second model, the government enters the chain directly by creating an integrator facility, which is responsible for packaging and coordination between facilities, and assumes the cost of packaging, and by merging publications together in one package, reduces the number of submissions and it supports the supply chain. For each of the above cases, a mathematical model was defined and a case study was conducted for 6307 customers and 119 districts of Tehran. According to the output of the models, the profit of each supplier including subsidies was more than the second model in the first model. However, the amount of subsidies paid in the first model is much higher than in the second model. By considering this issue and eliminating subsidies from profit calculations of the two models, the second model showed a more favorable performance in equal and full welfare in all regions. However, the first model had a better performance in conditions with different welfares in various regions. According to the results, in addition to subsidies, the government must enact laws that oblige publishers to complete welfare.</description> </item> <item> <title>Impact of Work-Life Balance and Work Engagement on Innovative Work Behavior</title> <link>http://www.ijsom.com/article_2946.html</link> <description>This research explores the influence of work-life balance and work participation on innovative work behavior at PT Astra Agro Lestari Tbk. Using a quantitative approach with multiple linear regression analysis, this research involved 98 employees as research samples. The results of the normality test show that the data is usually distributed, while the linearity test indicates a linear relationship between work-life balance, work participation, and innovative work behavior. The regression analysis results show that work-life balance and work participation have a positive and significant effect on innovative work behavior, with an R&amp;amp;sup2; value of 0.291. This means that the two independent variables explain 29.1% of the variability in innovative work behavior. This study emphasizes the importance of work-life balance and work participation in driving innovation in the workplace. Companies can increase employees ' innovative capabilities by balancing work and personal life and employee engagement. These findings provide insight for the management of PT Astra Agro Lestari Tbk to develop policies that support work-life balance and active participation as strategies to increase innovative behavior and organizational competitiveness.</description> </item> <item> <title>Assessment of a Hybrid Machine Learning Algorithm in Healthcare Management for Predicting Diabetes Disease</title> <link>http://www.ijsom.com/article_2945.html</link> <description>Diabetes Mellitus is one of the most chronic diseases in all over the world. Every year, many people die due to this disease in all countries. Therefore, identifying early detection methods for this disease can reduce its mortality. Today, many diseases can be diagnosed and prevented from progressing by using data mining techniques and machine learning algorithms. In this paper, diabetes prediction has been aimed by comparing the efficiency of several classical machine-learning techniques. For this reason, for the sake of diabetes prediction algorithms such as Na&amp;amp;iuml;ve Bayes, Logistic Regression (LR), Multi-Layer Perceptron (MLP), Sequential Minimal Optimization (SMO), J48, Random Forest (RF), Regression Tree (RT) algorithms and a new hybrid algorithm based on Multi-Verse Optimizer (MVO) and Multi-Layer Perceptron (MLP) algorithms are employed for this evaluation based on Accuracy (ACC) Indicator and Area under Curve (AUC) criteria. Numerous and diverse methods and algorithms have been used to predict diabetes. Each of these algorithms has been effective in predicting diabetes with a different level of accuracy. Our goal in this research is to introduce a new combined algorithm that has the highest level of accuracy in predicting diabetes compared to the old frequent algorithms so that it can help people in the timely treatment of this disease. In the structure of the MLP algorithm, the backpropagation algorithm is used for training. This article uses the MVO algorithm to train the MLP instead of the backpropagation algorithm, which built the hybrid algorithm called MVO-MLP. The accuracy results and the area under the ROC diagram Indicated that the proposed hybrid algorithm increases the accuracy by 107% compared to the MLP algorithm with the default structure. The outcomes of the accuracy of the new model are also higher than other algorithms used in this article</description> </item> <item> <title>A Review Study on Advancements in Reverse Supply Chain Management for Industrial Waste Management Process</title> <link>http://www.ijsom.com/article_2947.html</link> <description>Supply chain management (SCM) is the active management of supply chain activities to optimize customer value and establish a sustainable competitive advantage. It demonstrates that supply chain management firms are actively working to establish and run source chains as profitably and well as they can. The activities that comprise the supply chain include the development of products, procurement, manufacturing, shipping, and the data systems wanted to oversee these processes. This review presents information. SCM was introduced in the opening paragraph of this page, which was followed by information about the participants and the procedures used by different businesses. It employs sustainable supply chain management (SSCM), which offers five-dimensional sustainable approaches, and presents GSCM in this study. The needs in the industrial industry's supply chain are continuously presented. Accordingly, the waste material management process is presented for different manufacturing industries, however, it consists of waste management methods like disposal method, landfill, and incineration. Additionally, this study presents detailed information about reverse Supply Chain Management (RSCM), their concept and process are explained in this review. The review describes the state of the art in survey technology, the methodology of implementation, the definition and motivation of the research topic, current trends and advancements, and the goal of the study. Reviewers came to the conclusion that RSCM controls the waste product well as a result. Utilizing the components and materials of returned goods to cut down on raw material usage and expenses is the focus of supply management in reverse logistics (RL). In future, reverse logistic SCM is introduced in the automobile industry to efficiently manage automobile waste.</description> </item> <item> <title>Green Ports Assessment Model regarding Uncertainty by Best-Worst and Hesitant Fuzzy VIKOR Methods: Iranian Ports</title> <link>http://www.ijsom.com/article_2909.html</link> <description>These days environmental protection has crucial importance in different scopes of scientific research due to the environmental climate change, and popular concern about the future of the world. Ports and maritime transportation also play a noteworthy role in sustainability owing to the fact they are known as crucial and significant economic hubs all around the world. Hence, here environmental factors associated with the ports have been illustrated and according to the experts &amp;amp;lsquo;attitudes by using the Best-Worst method (BWM) to find less incompatibility, the criteria&amp;amp;rsquo;s weight would have been calculated. Emissions of pollutants into the waters, environmental pollution, and General waste handling are the best, and Technology and Education, Hazardous waste handling, and Port staff training are the worst criteria respectively. Afterward, owing to the ambiguity in experts &amp;amp;lsquo;attitudes, the combination of the VIKOR decision-making method and the hesitant fuzzy has been utilized in order to compare alternatives through uncertainty in data and to decrease related errors. Finally, the proposed assessment model has been examined with sensitivity analysis in a real case of Iranian Ports.</description> </item> <item> <title>A Multi Echelon Location-Routing-Inventory Model for a Supply Chain Network: NSGA II and Multi-Objective Whale Optimization Algorithm</title> <link>http://www.ijsom.com/article_2913.html</link> <description>In this study, we aim to explore the modeling and solution approach for a multi-objective location-routing-inventory problem. The focus is on planned transportation with the goal of minimizing total costs and reducing the maximum working hours of drivers. To achieve these objectives, we need to consider the routing of vehicles between customers and distribution centers, as well as the optimal allocation of product transfer flow between the production center and customers. Therefore, the proposed model incorporates location, routing-inventory, and allocation simultaneously. To solve the two-objective model, we employed the Epsilon-constraint method for small-sized problems. For large-sized problems, we utilized the NSGA-II and MOWOA meta-heuristic algorithms with a new chromosome. The computational results indicate that in order to reduce the maximum working hours of drivers, it is necessary to increase the number of vehicles and minimize travel distances. However, this leads to higher costs due to vehicle utilization and the need for constructing distribution centers closer to customers, which in turn increases construction costs. Finally, based on the analysis, the NSGA-II algorithm outperformed the MOWOA algorithm with a weighted value of 0.983 compared to 0.016, making it the selected algorithm.</description> </item> <item> <title>Designing a Sustainable Model for Providing Health Services Based on the Internet of Things and Meta-Heuristic Algorithms</title> <link>http://www.ijsom.com/article_2919.html</link> <description>In this article, a health service delivery model based on the Internet of Things (IoT) under uncertainty is presented. The considered model includes a set of patients, doctors, vehicles, and services that should be provided in the shortest time and cost. The most important decisions of the network include the allocation of specialist doctors to patients, the routing of vehicles, and doctors to provide health services. The dataset of the problem has been provided to the hospital and centers using IoT tools and an integration framework has been designed for this problem. The results of solving the numerical examples show that to reduce the service delivery time and the distance traveled by vehicles, the design costs of the model should be increased. Also, the increase in the rate of uncertainty during service delivery leads to an increase in total costs in the health system. In this article, Non-Dominated Sorting Genetic Algorithm II (NSGA-II), Multi-Objective Particle Swarm Optimization (MOPSO), and Multi-objective imperialist Competitive algorithm (MOICA) were proposed to solve the model, and the results showed that the proposed methods are more efficient than the exact methods. These algorithms have achieved close to optimal results in the shortest possible time. Also, the calculation results in large numerical examples show the high efficiency of the MOICA.</description> </item> <item> <title>Optimizing Supply Chain Sustainability through AI-Driven Policies and Integrator Facility</title> <link>http://www.ijsom.com/article_2930.html</link> <description>Supply chains play a pivotal role in shaping a nation's economic landscape, making their sustainability a paramount concern. However, there is a notable lack of comprehensive policy frameworks addressing this crucial issue. This research aims to fill this gap by introducing two novel policy approaches. Our study focuses on optimizing supply chain networks through the application of AI-driven policies. We analyze the effectiveness of two specific policies: one involving subsidies for suppliers and the other entailing government intervention via an integrator facility for packaging and coordination. To assess these policies, we develop mathematical models and optimize them using the Firefly Algorithm (FA). The research outcomes distinctly reveal that subsidies confer a discernible advantage upon the first model, underscoring their role in shaping its efficacy. Intriguingly, the second model emerges as a formidable contender, particularly when untethered from the support of subsidies. This illuminates the inherent robustness of the second model's design, standing resilient even without the crutch of financial incentives. Beyond the realm of subsidies, the research imparts a profound insight into the essence of holistic policy paradigms, underpinned by AI-driven methodologies. It champions the necessity for a comprehensive approach that extends beyond mere financial aid, advocating for the installation of regulatory frameworks that galvanize publishers' accountability. This multifaceted approach ensures that the trajectory of social welfare is seamlessly woven into the very fabric of the supply chain's functioning, securing a sustainable and equitable distribution of benefits.</description> </item> <item> <title>Optimizing Sustainability and Risk Management in Intelligent Supply Chains: A Case Study from Thailand</title> <link>http://www.ijsom.com/article_2932.html</link> <description>In this study, an exploration is undertaken to contribute significantly to the sustainable development of intelligent supply chains by investigating the optimization of the supply chain network within the realm of risk management, with specific attention devoted to resource reliability. The formalization of risk management and its integration into intelligent supply chain optimization is evaluated through an online survey involving leaders of enterprises in Thailand. A novel mathematical model aimed at enhancing risk mitigation while considering the availability of requisite resources is introduced and subsequently optimized utilizing GAMS software. To address the multi-objective nature inherent in the proposed model, an approach grounded in fuzzy theory is applied. The research outcomes illuminate the evolving role of risk mitigation within Thai enterprises, emphasizing its responsibility to provide assurances against potential risks. Despite notable strides in risk management, persistent challenges are underscored. Furthermore, emphasis is placed on the capacity of intelligent supply chains to adapt and efficaciously address dynamic risk factors in an ever-evolving world, aligning seamlessly with the principles of sustainable development.</description> </item> <item> <title>Hybrid Levenberg Marquardt and Back Propagation Neural Network for House Price Prediction in Taiwan</title> <link>http://www.ijsom.com/article_2937.html</link> <description>Price prediction is an influential tool in each market to enhance economic performance. In this regard, regression methods are often used. However, with the expansion of artificial intelligence, neural networks, machine learning, and deep learning, these methods can also be used for prediction. On the other hand, pricing in the housing market is always challenging, and forecasting the house price has been one of the concerns of economic activists in this field. Accordingly, in this research, a hybrid Levenberg Marquardt (LM) and Back Propagation (BP) neural network has been developed to forecast housing prices in Taiwan. This artificial intelligence method can provide a suitable forecast for housing price trends in the future by using the information in the form of Input and Output. This method uses inputs such as inflation rate, bank interest rate, minimum wage, and gross domestic product (GDP). Moreover, the housing price index is considered as the output of the model. In order to implement the proposed method, data from Taiwan from 1998 to 2022 was used. In this regard, a percentage of this data is used as training data, and the rest is used as test data in the artificial neural network. The results show that the RMSE of the proposed method is less than classic LM and BP methods. Finally, the proposed neural network will achieve the final housing price in Taiwan from 2023 through 2027. The results show that housing prices will trend upward in this country in the next five years.</description> </item> <item> <title>Targeted and Personalized Online Advertising in the Age of Artificial Intelligence (AI): A Literature Review and Research Agenda</title> <link>http://www.ijsom.com/article_2948.html</link> <description>This study aims to provide a comprehensive evaluation of current machine learning (ML) algorithms employed in targeted and personalized advertising. It reveals key findings and conclusions from a wide range of sources, offering readers a concise summary. The study addresses the gap by identifying and analyzing the most significant machine learning-based targeting methods utilized in the recent studies. This helps readers understand the strengths and weaknesses of different approaches and keeps them up-to-date with the most recent advancements and best practices. Employing the PRISMA methodology, the review systematically examines existing literature on ML-driven targeted advertising. It identifies effective ML methods and strategies, presenting real-world examples to illustrate their practical implementation. Reviewing key findings from existing literature, the analysis identifies the most effective ML methods for targeted advertising. It also examines three research questions across three key dimensions: targeting, personalizing, and predicting customer preferences. This study proposes a novel theoretical framework that elucidates the application of ML in targeted advertising. Specifically, the study explores ML algorithms that enhance precision in each dimension. Key models include Long Short-Term Memory (LSTM) networks for analyzing historical customer data, Convolutional Neural Networks (CNN) for image recognition tasks, and Factorization Machines for capturing feature interactions in click-through rate (CTR) predictions. Additionally, traditional models such as logistic regression, decision trees, random forests, and support vector machines (SVM) are utilized for classification tasks, while unsupervised learning techniques like k-means clustering and hierarchical clustering facilitate user segmentation based on behavioral and demographic similarities. These models collectively enable marketers to derive actionable insights, optimize advertising content, and improve overall campaign performance. By consolidating key findings from existing literature on ML-driven targeted advertising, this study offers a valuable resource for understanding current trends and gaps. It also proposes future research directions, highlighting potential areas for further exploration, which can inspire new studies and innovations in the field.</description> </item> <item> <title>A New Multi-Objective Location Routing Problem with Hybrid Fuzzy-Stochastic Approach by Considering Capacity Restrictions: Model, Solution and Application</title> <link>http://www.ijsom.com/article_2949.html</link> <description>This study proposes a multi-objective location-routing problem considering the capacity of vehicles to decline the system's costs. The model considers probabilistic times of traveling, service, and waiting by vehicles while guaranteeing the least probability which the cumulative values of these parameters are less than a pre-determined value when minimization of this value is considered an objective function.&amp;amp;nbsp; To cope with uncertainty, fuzzy numbers for important parameters of customer demand, vehicle capacity, variable and fixed transportation costs, and depot opening costs are used. Moreover, the nonlinear constraints are linearized to reduce computational time. We also use a fuzzy ranking method to transform the presented model into an equivalent auxiliary crisp model. As the model is NP-hard, we introduce a novel Multi-Objective Imperialist Competitive Algorithm (MOICA) to address the issue. The efficacy of the presented MOICA is evaluated by comparing its performance against two well-established multi-objective metaheuristics, Pareto Archived Evolution Strategy (PAES), and Non-Dominated Sorting Genetic Algorithm-II (NSGA-II). Leveraging Response Surface Methodology (RSM), the mutation and crossover operators employed by each algorithm were meticulously tuned. Subsequently, the performance of all three algorithms was examined using four benchmark comparison metrics across a range of established benchmark examples. The results demonstrably substantiate the superiority of the proposed MOICA in achieving optimal solutions.</description> </item> <item> <title>The Impact of Green Logistics Management Practices on Manufacturing Firms' Sustainability Performance in Ghana and Indonesia</title> <link>http://www.ijsom.com/article_2950.html</link> <description>This study investigates the impact of four dimensions of Green Logistics Management Practices (GLMP)&amp;amp;ndash;Inbound Logistics (IL), Outbound Logistics (OL), Green Operation and Production (GOP), and Reverse Logistics (RS)&amp;amp;ndash;on economic, environmental, and social performance, which represent the sustainability dimensions in both Ghana and Indonesia. This study compares the impacts of the Green Logistics Management Practices (GLMP) in Ghana and Indonesia, considering their respective economic and environmental contexts. It aims to understand how GLMP contribute to sustainability in rapidly industrializing regions, filling a gap in the literature on the comparative effects of GLMP in different socio-economic environments. The data collection process involved the use of a plant-level survey methodology, a cross-sectional survey conducted through email, and in-person to gather information from manufacturing firms in both countries. A total of 265 manufacturing companies were randomly selected from each country for the survey, ensuring that each participant had an equal opportunity to be included, thus maintaining the sample equality between the two countries. The application of structural equation modeling demonstrates the presence of significant relationships between the dimensions of GLMP and sustainability performance in both contexts. We proposed a conceptual framework and conducted an empirical investigation into the relationship between GLMP and sustainability performance (SP) in two countries with distinct continental characteristics. We used a set of hypotheses and employed structural equation modelling (SEM) to test our proposed framework. This study provides valuable insights into the practical implications of implementing GLMPs to improve the overall performance. This study addresses a significant void in the literature by offering a comparative analysis of Ghana and Indonesia. This analysis offers distinct perspectives on the correlation between GLMPs and sustainability performance. The lack of previous comparative studies highlights the originality of this research, providing a significant contribution and establishing a groundwork for future research opportunities in various geographical contexts.</description> </item> </channel> </rss>