Empirical parameterization of the Elo Rating System

TL;DR

This paper introduces a data-driven method for empirically tuning Elo rating system parameters by maximizing predictive accuracy, improving its adaptability and performance across various game types.

Contribution

It presents a generalizable framework for empirically optimizing rating system parameters using game data, applicable to Elo and other systems, including multiplayer scenarios.

Findings

Enhanced predictive accuracy of match outcomes

Effective parameter tuning on real and simulated data

Framework adaptable to various rating systems

Abstract

This study aims to provide a data-driven approach for empirically tuning and validating rating systems, focusing on the Elo system. Well-known rating frameworks, such as Elo, Glicko, TrueSkill systems, rely on parameters that are usually chosen based on probabilistic assumptions or conventions, and do not utilize game-specific data. To address this issue, we propose a methodology that learns optimal parameter values by maximizing the predictive accuracy of match outcomes. The proposed parameter-tuning framework is a generalizable method that can be extended to any rating system, even for multiplayer setups, through suitable modification of the parameter space. Implementation of the rating system on real and simulated gameplay data demonstrates the suitability of the data-driven rating system in modeling player performance.