Predicting player lifetime value for online social games

Jiesi Cheng, Daniel Zeng

Research output: Contribution to conferencePaper

Abstract

Online social gaming is experiencing rapid growth and gaining explosive popularity worldwide. One crucial problem facing the game developers is to accurately estimate the game player's lifetime value (PLV) in real time, such that more targeted advertising, and more efficient resource allocation may become feasible. In this study, we first conducted an empirical study to identify significant features that are indicative of PLV. The results demonstrated that friends' activities can serve as an additional powerful predictor of a player's PLV. Based on this observation, we proposed a perceptron-based online PLV prediction model considering both individual and friendship information. Preliminary results have shown that the model can be effectively used in online PLV prediction, by evaluating against commonly-used benchmark methods. More importantly, the use of friendship information further improves the prediction accuracy.

Original languageEnglish (US)
Pages199-204
Number of pages6
StatePublished - Jan 1 2011
Event21st Workshop on Information Technologies and Systems, WITS 2011 - Shanghai, China
Duration: Dec 3 2011Dec 4 2011

Other

Other21st Workshop on Information Technologies and Systems, WITS 2011
CountryChina
CityShanghai
Period12/3/1112/4/11

ASJC Scopus subject areas

  • Information Systems

Fingerprint Dive into the research topics of 'Predicting player lifetime value for online social games'. Together they form a unique fingerprint.

  • Cite this

    Cheng, J., & Zeng, D. (2011). Predicting player lifetime value for online social games. 199-204. Paper presented at 21st Workshop on Information Technologies and Systems, WITS 2011, Shanghai, China.