<?xml version="1.0" encoding="UTF-8"?> <article key="pdf/10012320" mdate="2021-12-02 00:00:00"> <author>Mark Harmon and Abdolghani Ebrahimi and Patrick Lucey and Diego Klabjan</author> <title>Predicting Shot Making in Basketball Learnt from Adversarial Multiagent Trajectories</title> <pages>973 - 983</pages> <year>2021</year> <volume>15</volume> <number>11</number> <journal>International Journal of Sport and Health Sciences</journal> <ee>https://publications.waset.org/pdf/10012320</ee> <url>https://publications.waset.org/vol/179</url> <publisher>World Academy of Science, Engineering and Technology</publisher> <abstract>In this paper, we predict the likelihood of a player making a shot in basketball from multiagent trajectories. To approach this problem, we present a convolutional neural network (CNN) approach where we initially represent the multiagent behavior as an image. To encode the adversarial nature of basketball, we use a multichannel image which we then feed into a CNN. Additionally, to capture the temporal aspect of the trajectories we use &amp;ldquo;fading.&amp;rdquo; We find that this approach is superior to a traditional FFN model. By using gradient ascent, we were able to discover what the CNN filters look for during training. Last, we find that a combined FFNCNN is the best performing network with an error rate of 39.</abstract> <index>Open Science Index 179, 2021</index> </article>