Competitive Balance in Team Sports Games
This addresses matchmaking for player satisfaction in multiplayer online games, representing an incremental improvement.
The paper tackles the problem of predicting competitive balance in team sports games by showing that using final score difference provides better prediction than traditional skill-based methods, with a linear model achieving almost the same performance as neural networks while offering 100x faster inference speed.
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.