Scalable Framework for Basketball Game Prediction Combining Image Processing XGBoost and Enhanced Support Vector Machine
Main Article Content
Abstract
A significant goal for sports team management is establishing a reliable method for analyzing players’ performance. This research suggested a better method for predicting sporting events, including the final score of a basketball game, by combining adaptive weighted features with machine learning algorithms. Hence, this paper proposes Image Processing with XGBoost and the Enhanced Support Vector Machine Algorithm (XGB-SVM) to construct a real-time basketball game result prediction model. The model effectively quantified the study’s key variables that influenced basketball game results and simulated the prediction of game outcomes at different times of basketball games. The study’s findings proved that the XGBoost algorithm could accurately forecast the results of basketball games. There has been an enduring correlation between the results of the basketball game and key performance metrics, including defensive rebounds, field goal percentage, and turnovers. Incorporating Image Processing, XGBoost, and the Enhanced Support Vector Machine Algorithm, the real-time prediction model for basketball game outcomes achieves outstanding and easily interpretable results. Because of this, it can accurately forecast and evaluate basketball score forecasts. The results can give credibility to the team’s player management decisions. The proposed method increases the player positioning data ratio by 96.8%, shot trajectory ratio by 98.3%, historical performance data ratio by 91.7%, efficiency ratio by 98.5%, and accuracy ratio by 92.7% compared to other existing methods.
Article Details

This work is licensed under a Creative Commons Attribution 4.0 International License.