SPORTS SCORE PREDICTION USING ARTIFICIAL INTELLIGENCE

Predicting the outcomes of sports events, particularly the final scores, has significant applications across sports analytics, betting, team performance assessment, and fan engagement. This paper investigates the use of machine learning algorithms for predicting the scores of football (soccer) matches, focusing on four well-established algorithms: Decision Trees (DT), Random Forests (RF), Support Vector Machines (SVM), and Deep Neural Networks (DNN). We compare the predictive accuracy of these algorithms using a dataset of historical football match data, including features such as team statistics, player performance, match conditions, and more.[1] Our results indicate that while DNNs outperform traditional models in terms of prediction accuracy, Random Forests also deliver competitive results. Furthermore, Decision Trees and SVMs show limited success in capturing the complex patterns inherent in sports data.[2] These findings highlight the potential of machine learning in sports score prediction and provide insights into selecting appropriate models for different prediction tasks.