We propose a novel two-stage data-analytic modeling approach to gamer matching for multiplayer video games. In the first stage, we build a hidden Markov model to capture how gamers' latent engagement state evolves as a function of their game-play experience and outcome and the relationship between their engagement state and game-play behavior. We estimate the model using a data set containing detailed information on 1,309 randomly sampled gamers' playing histories over 29 months. We find that high-, medium-, and low-engagement-state gamers respond differently to motivations, such as feelings of achievement and need for challenge. For example, a higher per-period total score (achievement) increases the engagement of gamers in a low or high engagement state but not those in a medium engagement state; gamers in a low or medium engagement state enjoy within-period score variation (challenge), but those in a high engagement state do not. In the second stage, we develop a matching algorithm that learns (predicts) the gamer's current engagement state on the fly and exploits that learning to match the gamer to a round to maximize game-play. Our algorithm increases gamer game-play volume and frequency by 4%–8% conservatively, leading to economically significant revenue gains for the company.
Gaming Social Capital: Exploring Civic Value in Multiplayer Video Games
