Forecasting Soccer Matches through Distributions

TL;DR

This paper introduces a novel approach for predicting soccer match outcomes by modeling shot distributions and combining ELO ratings with machine learning, demonstrating positive betting returns despite challenge constraints.

Contribution

It presents a new distribution-based forecasting method that integrates ELO ratings and machine learning for improved soccer outcome predictions.

Findings

The approach yields positive betting returns.

Modeling shot distributions improves forecast accuracy.

Combining ELO ratings with machine learning enhances predictions.

Abstract

Forecasting sporting events encapsulate a compelling intellectual endeavor, underscored by the substantial financial activity of an estimated $80 billion wagered in global sports betting during 2022, a trend that grows yearly. Motivated by the challenges set forth in the Springer Soccer Prediction Challenge, this study presents a method for forecasting soccer match outcomes by forecasting the shot quantity and quality distributions. The methodology integrates established ELO ratings with machine learning models. The empirical findings reveal that, despite the constraints of the challenge, this approach yields positive returns, taking advantage of the established market odds.