'Level Up': Leveraging Skill and Engagement to Maximize Player Game-Play in Online Video Games

摘要

We propose a novel two-stage data-analytic modeling approach combining theories, statistical analysis, and optimization techniques to model player engagement as a function of motivation to maximize customer game-play via matching in the large and growing online video game industry. In the first stage, we build a hidden Markov model (HMM) based on theories of customer engagement and gamer motivation to capture the evolution of gamers' latent engagement state and state-dependent participation behavior. We then calibrate the HMM using a longitudinal data set, obtained from a major international video gaming company, that contains detailed information on 1,309 randomly sampled gamers' playing histories over a period of 29 months comprising more than 700,000 unique game rounds. We find that high-, medium-, and low-engagement-state gamers respond differently to motivations, such as feelings of effectance and need for challenge. In the second stage, we use the results from the first stage to develop a matching algorithm that learns (infers) 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.