User behavior modelling approach for churn prediction in online games

Zoheb H. Borbora, Jaideep Srivastava

Research output: Chapter in Book/Report/Conference proceedingConference contribution

17 Citations (Scopus)

Abstract

Massively Multiplayer Online Role-Playing Games (MMORPGs) are persistent virtual environments where millions of players interact in an online manner. Game logs capture player activities in great detail and user behavior modeling approaches can help to build accurate models of player behavior from these logs. We are interested in modeling player churn behavior and we use a lifecycle-based approach for this purpose. In a player lifecycle-based approach, we analyze the activity traits of churners in the weeks leading up to their point of leaving the game and compare it with the activity traits of a regular player. We identify several intuitive yet distinct behavioral profiles associated with churners and active players which can discriminate between the two populations. We use these insights to propose three semantic dimensions of engagement, enthusiasm and persistence to construct derived features. Using three session-related variables and the features derived from them, we are able to achieve good classification performance with the churn prediction models. Finally, we propose a distance-based classification scheme, which we call wClusterDist, which benefits from these distinct behavioral profiles of the two populations. Experimental results show that the proposed classification scheme is well-suited for this problem formulation and its performance is better than or comparable to other traditional classification schemes.

Original languageEnglish
Title of host publicationProceedings - 2012 ASE/IEEE International Conference on Privacy, Security, Risk and Trust and 2012 ASE/IEEE International Conference on Social Computing, SocialCom/PASSAT 2012
Pages51-60
Number of pages10
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event2012 ASE/IEEE International Conference on Social Computing, SocialCom 2012 and the 2012 ASE/IEEE International Conference on Privacy, Security, Risk and Trust, PASSAT 2012 - Amsterdam, Netherlands
Duration: 3 Sep 20125 Sep 2012

Other

Other2012 ASE/IEEE International Conference on Social Computing, SocialCom 2012 and the 2012 ASE/IEEE International Conference on Privacy, Security, Risk and Trust, PASSAT 2012
CountryNetherlands
CityAmsterdam
Period3/9/125/9/12

Fingerprint

Virtual reality
Semantics

Keywords

  • churn prediction
  • distance-based classification
  • lifecycle analysis
  • time-series clustering
  • user behavior modelling

ASJC Scopus subject areas

  • Safety, Risk, Reliability and Quality

Cite this

Borbora, Z. H., & Srivastava, J. (2012). User behavior modelling approach for churn prediction in online games. In Proceedings - 2012 ASE/IEEE International Conference on Privacy, Security, Risk and Trust and 2012 ASE/IEEE International Conference on Social Computing, SocialCom/PASSAT 2012 (pp. 51-60). [6406269] https://doi.org/10.1109/SocialCom-PASSAT.2012.84

User behavior modelling approach for churn prediction in online games. / Borbora, Zoheb H.; Srivastava, Jaideep.

Proceedings - 2012 ASE/IEEE International Conference on Privacy, Security, Risk and Trust and 2012 ASE/IEEE International Conference on Social Computing, SocialCom/PASSAT 2012. 2012. p. 51-60 6406269.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Borbora, ZH & Srivastava, J 2012, User behavior modelling approach for churn prediction in online games. in Proceedings - 2012 ASE/IEEE International Conference on Privacy, Security, Risk and Trust and 2012 ASE/IEEE International Conference on Social Computing, SocialCom/PASSAT 2012., 6406269, pp. 51-60, 2012 ASE/IEEE International Conference on Social Computing, SocialCom 2012 and the 2012 ASE/IEEE International Conference on Privacy, Security, Risk and Trust, PASSAT 2012, Amsterdam, Netherlands, 3/9/12. https://doi.org/10.1109/SocialCom-PASSAT.2012.84
Borbora ZH, Srivastava J. User behavior modelling approach for churn prediction in online games. In Proceedings - 2012 ASE/IEEE International Conference on Privacy, Security, Risk and Trust and 2012 ASE/IEEE International Conference on Social Computing, SocialCom/PASSAT 2012. 2012. p. 51-60. 6406269 https://doi.org/10.1109/SocialCom-PASSAT.2012.84
Borbora, Zoheb H. ; Srivastava, Jaideep. / User behavior modelling approach for churn prediction in online games. Proceedings - 2012 ASE/IEEE International Conference on Privacy, Security, Risk and Trust and 2012 ASE/IEEE International Conference on Social Computing, SocialCom/PASSAT 2012. 2012. pp. 51-60
@inproceedings{fb24643ad6e546ff8543c66474c2119e,
title = "User behavior modelling approach for churn prediction in online games",
abstract = "Massively Multiplayer Online Role-Playing Games (MMORPGs) are persistent virtual environments where millions of players interact in an online manner. Game logs capture player activities in great detail and user behavior modeling approaches can help to build accurate models of player behavior from these logs. We are interested in modeling player churn behavior and we use a lifecycle-based approach for this purpose. In a player lifecycle-based approach, we analyze the activity traits of churners in the weeks leading up to their point of leaving the game and compare it with the activity traits of a regular player. We identify several intuitive yet distinct behavioral profiles associated with churners and active players which can discriminate between the two populations. We use these insights to propose three semantic dimensions of engagement, enthusiasm and persistence to construct derived features. Using three session-related variables and the features derived from them, we are able to achieve good classification performance with the churn prediction models. Finally, we propose a distance-based classification scheme, which we call wClusterDist, which benefits from these distinct behavioral profiles of the two populations. Experimental results show that the proposed classification scheme is well-suited for this problem formulation and its performance is better than or comparable to other traditional classification schemes.",
keywords = "churn prediction, distance-based classification, lifecycle analysis, time-series clustering, user behavior modelling",
author = "Borbora, {Zoheb H.} and Jaideep Srivastava",
year = "2012",
doi = "10.1109/SocialCom-PASSAT.2012.84",
language = "English",
isbn = "9780769548487",
pages = "51--60",
booktitle = "Proceedings - 2012 ASE/IEEE International Conference on Privacy, Security, Risk and Trust and 2012 ASE/IEEE International Conference on Social Computing, SocialCom/PASSAT 2012",

}

TY - GEN

T1 - User behavior modelling approach for churn prediction in online games

AU - Borbora, Zoheb H.

AU - Srivastava, Jaideep

PY - 2012

Y1 - 2012

N2 - Massively Multiplayer Online Role-Playing Games (MMORPGs) are persistent virtual environments where millions of players interact in an online manner. Game logs capture player activities in great detail and user behavior modeling approaches can help to build accurate models of player behavior from these logs. We are interested in modeling player churn behavior and we use a lifecycle-based approach for this purpose. In a player lifecycle-based approach, we analyze the activity traits of churners in the weeks leading up to their point of leaving the game and compare it with the activity traits of a regular player. We identify several intuitive yet distinct behavioral profiles associated with churners and active players which can discriminate between the two populations. We use these insights to propose three semantic dimensions of engagement, enthusiasm and persistence to construct derived features. Using three session-related variables and the features derived from them, we are able to achieve good classification performance with the churn prediction models. Finally, we propose a distance-based classification scheme, which we call wClusterDist, which benefits from these distinct behavioral profiles of the two populations. Experimental results show that the proposed classification scheme is well-suited for this problem formulation and its performance is better than or comparable to other traditional classification schemes.

AB - Massively Multiplayer Online Role-Playing Games (MMORPGs) are persistent virtual environments where millions of players interact in an online manner. Game logs capture player activities in great detail and user behavior modeling approaches can help to build accurate models of player behavior from these logs. We are interested in modeling player churn behavior and we use a lifecycle-based approach for this purpose. In a player lifecycle-based approach, we analyze the activity traits of churners in the weeks leading up to their point of leaving the game and compare it with the activity traits of a regular player. We identify several intuitive yet distinct behavioral profiles associated with churners and active players which can discriminate between the two populations. We use these insights to propose three semantic dimensions of engagement, enthusiasm and persistence to construct derived features. Using three session-related variables and the features derived from them, we are able to achieve good classification performance with the churn prediction models. Finally, we propose a distance-based classification scheme, which we call wClusterDist, which benefits from these distinct behavioral profiles of the two populations. Experimental results show that the proposed classification scheme is well-suited for this problem formulation and its performance is better than or comparable to other traditional classification schemes.

KW - churn prediction

KW - distance-based classification

KW - lifecycle analysis

KW - time-series clustering

KW - user behavior modelling

UR - http://www.scopus.com/inward/record.url?scp=84873643613&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873643613&partnerID=8YFLogxK

U2 - 10.1109/SocialCom-PASSAT.2012.84

DO - 10.1109/SocialCom-PASSAT.2012.84

M3 - Conference contribution

SN - 9780769548487

SP - 51

EP - 60

BT - Proceedings - 2012 ASE/IEEE International Conference on Privacy, Security, Risk and Trust and 2012 ASE/IEEE International Conference on Social Computing, SocialCom/PASSAT 2012

ER -