Customer Churn Prediction in Virtual Worlds

Hsiu Yu Liao*, Kuan Yu Chen, Duen-Ren Liu, Yi Ling Chiu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

With the emerging of social network websites, more and more social network online games are booming. Players have more alternatives of VWs games, while platform providers suffer from the problems of high customer turnover rate and low-customer-loyalty. Therefore, building a churn prediction model to facilitate subsequent churn management and customer retention is the best core marketing strategy. In this paper, we put emphasis on modeling a hybrid classification, which takes monetary cost, user behavior and social neighbor features into consideration. The experimental results show that the proposed hybrid model is well-suited for this problem in virtual worlds comparing to the existing churn prediction methods applied in the traditional retail, and financial industry.

Original languageEnglish
Title of host publicationProceedings - 2015 IIAI 4th International Congress on Advanced Applied Informatics, IIAI-AAI 2015
EditorsSachio Hirokawa, Kiyota Hashimoto, Tokuro Matsuo, Tsunenori Mine
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages115-120
Number of pages6
ISBN (Electronic)9781479999583
DOIs
StatePublished - 12 Jul 2015
Event4th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2015 - Okayama, Japan
Duration: 12 Jul 201516 Jul 2015

Publication series

NameProceedings - 2015 IIAI 4th International Congress on Advanced Applied Informatics, IIAI-AAI 2015

Conference

Conference4th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2015
Country/TerritoryJapan
CityOkayama
Period12/07/1516/07/15

Keywords

  • RFM model
  • churn prediction
  • social influence
  • virtual world

Fingerprint

Dive into the research topics of 'Customer Churn Prediction in Virtual Worlds'. Together they form a unique fingerprint.

Cite this