ContactResumeResearchTeachingStudentsSoftwareAnimationMusic dark-mode: off

Skill-Based Matchmaking for Competitive Games

With proper skill-based matchmaking everyone can experience the joy of video games, playing with others who have skill levels. This maximizes engagement and minimizes the frustration of playing against mismatched opponents.

Abstract

Skill-based matchmaking is a crucial component of competitive multiplayer games and it is directly tied to how the players would enjoy the game. We present a simple matchmaking algorithm that aims to achieve a target win rate for all players, making long win/loss streaks less probable. It is based on the estimated skill levels of players. Therefore, we also present a rating estimation for players that does not require any game-specific information and purely relies on game outcomes. Our evaluation shows that our methods are effective in estimating a player's rating, responding to changes in rating, and achieving a desirable win rate that avoids long win/loss streaks in competitive two-player games.

Video games can be frustrating, especially without proper skill-based matchmaking. Winning a game is more fun when you are challenged and it is hard to enjoy a game after losing many times in a row. Proper skill-based matchmaking methods can not only protect players from long losing streaks but also make winning much more fun and stimulating.

We present methods for skill-based matchmaking for competitive two-player games that involve two distinct components:

• A novel rating estimation method that can accurately represent a player's skill level and quickly react to (sudden or gradual) changes in a player's skill level. It automatically avoids the shortcomings of prior methods (i.e. Elo, Glicko, and TrueSkill) in noisy/divergent estimations, slow convergence, and inadequate reactions to changing skill levels.
• An algorithm for skill-based matchmaking using the estimated ratings that promotes a desirable win rate, making long win/loss streaks less probable.

The algorithms we describe are easy to implement and do not require storing player's game histories.

Win or lose, video games are much more fun with proper matchmaking that leads to close games and engaging experiences, away from long losing streaks.

Presentation @ I3D 2024

Publications