UTILIZING MACHINE LEARNING ALGORITHMS TO RESOLVE SPORTS CONTRACT DISPUTES

Abstract

This study explores the application of machine learning, specifically Support Vector Machine (SVM) models, in resolving sports contract disputes. Text mining techniques, including TF-IDF (Term Frequency-Inverse Document Frequency), were employed to process and extract significant features from unstructured contract dispute judgment documents collected from the China Judgments Online. The dataset encompassed various dispute categories such as athlete and club contract disputes, advertising endorsement disputes, transfer contract disputes, event organization and venue disputes, and copyright disputes. The SVM model, utilizing the nu-SVC variant with an RBF kernel, demonstrated high precision across most categories, effectively handling the high-dimensional and complex nature of legal texts. Key metrics such as precision, recall, and F-measure were used to evaluate model performance. The results highlight the robustness and accuracy of machine learning in classifying and analyzing sports contract disputes, providing a valuable tool for legal professionals to enhance dispute resolution processes. This study underscores the potential of integrating advanced computational techniques with legal analysis to improve the efficiency and effectiveness of resolving contractual conflicts in the sports industry.