Reproducible Evaluation of Football Lottery Strategies: Leakage, Calibration, and Temporal Backtesting

Abstract

Sports Forecasting Evaluation poses a recurring problem of coordinating performance with evidence quality, resource limits, and transfer across settings. This article critically maps building evaluation protocols that resist hindsight, selection bias, and unstable league conditions. It synthesizes 1 focal paper with 12 independently retrieved publications verified through persistent DOI or publisher records. The analysis is organized around temporal splits, data leakage, calibration, transaction assumptions, and replication. A central precaution is not to treat reported gains as context-free quantities, the review compares task scope, modeling premises, and evaluation limits. Across the literature, a robust inference is that advances in sports forecasting evaluation become credible when behavior, measurement, and decision context are evaluated together and when uncertainty about selection effects is reported explicitly. The framework consequently connects method selection to application risk, identifies recurring threats to external validity, and proposes a research agenda centered on traceable baselines, scenario testing, and reusable evidence.