On prophesying online gamer departure

The current business model of online game companies usually depends on the sale of virtual items or monthly subscriptions in which gamers must pay for credits to continue their adventures in the virtual world. From the perspective of game operators, being able to predict how long people will stay in the game is crucial, since it directly affects their revenue. The duration for which a player will remain active in a game should correlate with the extent of his involvement in the virtual world. More often than not, this can be inferred from the player´s external behavior, such as how quickly his avatar advances to new levels and how much time he spends in the game every day. This study is an extension of our previous game hour analysis, in which we analyzed what time players enter the game´s virtual world and how long they stay in the game, and investigated whether a player´s future game hours can be predicted with his observed behaviour. Our goal in this study, then, is to provide a practical scheme for predicting player unsubscription that takes a player´s game hours as input and determines whether or not he will renew expiring subscription. Our rationale is that, if we can predict the departure of a player before he actually quits a game, the game operator can take remedial measures to prevent it from happening and improve the game along the way based on the feedback provided by such a player.