Competitive Balance in Team Sports Games

TL;DR

This paper explores improved methods for predicting competitive balance in team sports games, demonstrating that score difference and linear models with selected features can outperform traditional skill-based predictors with faster inference.

Contribution

It introduces the use of final score difference as a better prediction metric and shows that a linear model with selected features rivals neural networks in accuracy while being much faster.

Findings

Score difference improves prediction accuracy.

Linear models with selected features perform nearly as well as neural networks.

Faster inference makes the approach suitable for online matchmaking.

Abstract

Competition is a primary driver of player satisfaction and engagement in multiplayer online games. Traditional matchmaking systems aim at creating matches involving teams of similar aggregated individual skill levels, such as Elo score or TrueSkill. However, team dynamics cannot be solely captured using such linear predictors. Recently, it has been shown that nonlinear predictors that target to learn probability of winning as a function of player and team features significantly outperforms these linear skill-based methods. In this paper, we show that using final score difference provides yet a better prediction metric for competitive balance. We also show that a linear model trained on a carefully selected set of team and individual features achieves almost the performance of the more powerful neural network model while offering two orders of magnitude inference speed improvement. This shows significant promise for implementation in online matchmaking systems.