Tanvir, SifatShakerin, Tasmia2026-07-142026-07-141/1/20239.79835E+122-s2.0-85169296247https://hdl.handle.net/10361/28540Team formation is a crucial factor in any team's success in football. A player's performance varies on the position that they are playing at. To tap into the maximum potential of a player, finding t he appropriate position for that player is a must. The goal of this research is to determine and predict whether a player is actually playing in the most optimal position or not based on the skill-set, physique, and preference. The same concept can be applied in both video games and in real life. Eight datasets, each from one of the FIFA video games from year 2015 to 2020 have been used in this work. How reduction of certain categorical classes improved the accuracy has been discussed. Simultaneously, the reputation of players has also been predicted with satisfactory accuracy to analyze the quality of the datasets.135-138en-USFALSEClass imbalanceDecision treeFeature encodingFeature selectionFIFA video gameKNNNaïve bayesRandom forestComputational intelligence.Decision trees.Image processing.Televised soccer games.Conference Proceedings10.1109/JCSSE58229.2023.10202045