Championship Probability Prediction in the FIFA ASEAN Cup 2026 Challenge Division Using Logistic Regression

This study aims to develop a Logistic Regression model for predicting the championship probability of teams participating in the FIFA ASEAN Cup 2026 Challenge Division. The study employs a quantitative approach using five performance indicators, namely FIFA Ranking, Win Rate, Average Goals Scored, Average Goals Conceded, and Goal Difference. Historical data from 2020–2025 were used to develop and evaluate the prediction model, while data from 2026 were used to estimate the championship probability of the participating teams. The historical dataset consisted of 36 observations and was divided into training and testing datasets using an 80:20 stratified split. Prior to modeling, the predictor variables were prepared using data preprocessing and standardization to ensure that the variables were suitable for Logistic Regression. Model performance was evaluated using Accuracy, Precision, Recall, and F1-score. The results showed that the Logistic Regression model achieved an Accuracy of 62.50%, Precision of 50.00%, Recall of 66.67%, and F1-score of 57.14% on the testing dataset. The prediction results indicated that Hong Kong obtained the highest championship probability of 77.53%, followed by Myanmar at 68.59% and Cambodia at 53.06%. Laos recorded 28.01%, while Timor-Leste and Brunei Darussalam obtained 0.72% and 0.71%, respectively. These results indicate that Logistic Regression provides an interpretable machine learning approach for estimating championship probability based on multiple football performance indicators and can support quantitative analysis of team championship potential in the FIFA ASEAN Cup 2026 Challenge Division.