<![CDATA[The ASEAN Championship is the most prestigious football competition in Southeast Asia, bringing together the best national teams from ASEAN Football Federation (AFF) member countries. Due to the high level of competition among participants, predicting the likelihood of winning cannot rely solely on FIFA Rankings; it requires an analysis that considers various statistical indicators of national team performance. This study aims to develop a prediction model for the 2026 ASEAN Championship winner using the Extreme Gradient Boosting (XGBoost) algorithm, based on national team performance statistics. The variables utilized include FIFA Rankings, performance in the last 10 matches, goals scored, goals conceded, and head-to-head records. Research data were obtained from FIFA, the ASEAN Football Federation (AFF), and various international football statistical databases. Prior to model training, the data underwent preprocessing stages—including cleaning, normalization, and encoding—and the dataset was split into 80% for training and 20% for testing. Model evaluation was conducted using the Confusion Matrix, Accuracy, Precision, Recall, F1-Score, and Receiver Operating Characteristic–Area Under Curve (ROC-AUC). Evaluation results demonstrate that the XGBoost model performs exceptionally well, achieving Accuracy, Precision, Recall, and F1-Score values of 87.50% each, along with an AUC value of 0.94. Based on the predictions, Indonesia holds the highest probability of winning at 24.35%, followed by Vietnam (20.18%) and Thailand (16.42%). The findings indicate that the Extreme Gradient Boosting (XGBoost) algorithm is capable of generating an accurate, objective, and comprehensive prediction model for analyzing championship prospects based on a combination of national team performance indicators, thereby offering an effective approach for predictive analysis in football competitions.]]>
Copyrights © 2026
