|
Abstract:
|
Managers of Multiplayer Online Role-Playing Games (MORPGs) rely on predictions of key player responses to design timely interventions for monetization and player retention. However, the longitudinal data from these digital products pose several challenges in developing statistical algorithms that can generate efficient predictions of future player activities. For instance, the existence of online communities or guilds in these games complicate prediction since players who are part of the same guild have correlated behaviors and the guilds themselves evolve over time and, thus, have a dynamic effect on the future playing behavior of its members. Here, we propose a novel statistical framework for analyzing correlated player responses in MORPGs. Our framework incorporates both dependence across players, via focal player’s social connections with their friends, as well as time varying guild effects on the future playing behavior. On a large-scale data from a popular MORPG, the proposed framework provides superior predictions of key player responses over competing methods and predicts player correlations within each guild that are valuable for optimizing future promotional policies.
|
