Assessing win strength in MLB win prediction models

TL;DR

This paper evaluates how well machine learning models predict win strength in MLB games by relating predicted win probabilities to score differentials and explores their use in betting strategies, showing potential for profit with proper methods.

Contribution

It extends previous MLB win prediction work by analyzing the relationship between predicted win probabilities and actual win strength, and assesses their application in betting.

Findings

Most ML models show a relationship between predicted win probability and score differential.

Proper betting strategies using predicted probabilities can yield positive returns.

Naive betting with ML predictions can lead to significant losses.

Abstract

In Major League Baseball, strategy and planning are major factors in determining the outcome of a game. Previous studies have aided this by building machine learning models for predicting the winning team of any given game. We extend this work by training a comprehensive set of machine learning models using a common dataset. In addition, we relate the win probabilities produced by these models to win strength as measured by score differential. In doing so we show that the most common machine learning models do indeed demonstrate a relationship between predicted win probability and the strength of the win. Finally, we analyze the results of using predicted win probabilities as a decision making mechanism on run-line betting. We demonstrate positive returns when utilizing appropriate betting strategies, and show that naive use of machine learning models for betting lead to significant loses.