An AutoML-Based Framework for Season-Level League Ranking Prediction in Professional Football

Accurate forecasting of season-level performance in professional football has gained increasing importance because of its implications for financial planning and strategic decision-making. This study proposes an Automated Machine Learning (AutoML) framework to predict end-of-season point totals and final league rankings in the Turkish Trendyol Süper Lig, conceptualizing cumulative performance as a macro-level forecasting problem. The analysis used data from six consecutive seasons (2018/2019–2023/2024), with out-of-sample validation conducted in the subsequent season. The dataset integrates financial indicators, such as squad market value, with technical performance metrics. Feature engineering expands 17 baseline variables into 32 indicators capturing efficiency, dominance, disciplinary impact, and context-adjusted performance. To mitigate target leakage, variables directly encoding total points are excluded. Two complementary modeling strategies are employed. First, a learning-to-rank approach using XGBoost Ranker directly models league standings. Second, an AutoML-based regression framework estimates the total season points, from which rankings are derived. Model performance is evaluated using Spearman’s rank correlation coefficient and mean absolute error. The ranking-based model achieves a correlation of 0.91, while the AutoML-optimized ExtraTrees Regressor improves this to 0.95, with an average prediction error of approximately 5–6 points. These findings demonstrate the effectiveness of the rank-sensitive predictive framework. Beyond predictive performance, the results indicate that efficiency and dominance-oriented performance indicators play a more decisive role in season-end success than possession-based metrics. This suggests that data-driven recruitment and squad planning strategies should prioritize players who contribute to scoring efficiency and competitive balance rather than purely volume-based attributes.