Churn prediction for high-value players in casual social games
Abstract
Predicting when players will leave a game creates a unique opportunity to increase players' lifetime and revenue contribution. Players can be incentivized to stay, strategically cross-linked to other games in the company's portfolio or, as a last resort, be passed on to other companies through in-game advertisement. This paper focuses on predicting churn for highvalue players of casual social games and attempts to assess the business impact that can be derived from a predictive churn model. We compare the prediction performance of four common classification algorithms over two casual social games, each with millions of players. Furthermore, we implement a hidden Markov model to explicitly address temporal dynamics. We find that a neural network achieves the best prediction performance in terms of area under curve (AUC). In addition, to assess the business value of churn prediction, we design and implement an A/B test on one of the games, using free in-game currency as an incentive to retain players. Test results indicate that contacting players shortly before the predicted churn event substantially improves the effectiveness of communication with players. They further show that giving out free in-game currency does not significantly impact the churn rate or monetization of players. This suggests that players can only be retained by remarkably changing their gameplay experience ahead of the churn event and that cross-linking may be the more effective measure to deal with churning players.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
Hidden Markov Models for Time Series: An Introduction Using R
Zucchini, W., & MacDonald, I. L. (2009) · Thammasat University Digital Collections · Cited by 686 · see citing works
Hidden Markov Models for Time Series
Zucchini, W., & MacDonald, I. L. (2009) · doi:10.1201/9781420010893 · Cited by 449 · see citing works
Coussement, K., & den Poel, D. V. (2006) · Expert Systems with Applications · doi:10.1016/j.eswa.2006.09.038 · Cited by 432 · see citing works
Social ties and their relevance to churn in mobile telecom networks
Dasgupta, K., Singh, R., Viswanathan, B., Chakraborty, D., Mukherjea, S., Nanavati, A. A., & Joshi, A. (2008) · International Conference on Extending Database Technology (EDBT) · doi:10.1145/1353343.1353424 · Cited by 333 · see citing works
Burez, J., & den Poel, D. V. (2006) · Expert Systems with Applications · doi:10.1016/j.eswa.2005.11.037 · Cited by 241 · see citing works
Churn Prediction in MMORPGs: A Social Influence Based Approach
Kawale, J., Pal, A., & Srivastava, J. (2009) · 2009 International Conference on Computational Science and Engineering · doi:10.1109/cse.2009.80 · Cited by 176 · see citing works
Predicting player churn in the wild
Hadiji, F., Sifa, R., Drachen, A., Thurau, C., Kersting, K., & Bauckhage, C. (2014) · 2014 IEEE Conference on Computational Intelligence and Games · doi:10.1109/cig.2014.6932876 · Cited by 154 · see citing works
A Neural Network based Approach for Predicting Customer Churn in Cellular Network Services
Sharma, A., Prabin, D., & Panigrahi, K. (2013) · Cited by 151 · see citing works
Social ties and their relevance to churn in mobile telecom networks
Dasgupta, K., Singh, R., Viswanathan, B., et al. (2008) · doi:10.1145/1352431.1352512 · Cited by 105 · see citing works
Bauckhage, C., Kersting, K., Sifa, R., et al. (2012) · IEEE Conference on Computational Intelligence and Games (CIG) · doi:10.1109/cig.2012.6374148 · Cited by 103 · see citing works
A Neural Network based Approach for Predicting Customer Churn in Cellular Network Services
Sharma, A., & Panigrahi, P. K. (2011) · International Journal of Computer Applications · doi:10.5120/3344-4605 · Cited by 79 · see citing works
Churn Prediction: Does Technology Matter?
Hadden, J., Tiwari, A., Roy, R., et al. (2008) · doi:10.5281/zenodo.1055858 · Cited by 72 · see citing works
User Behavior Modelling Approach for Churn Prediction in Online Games
Borbora, Z. H., & Srivastava, J. (2012) · doi:10.1109/socialcom-passat.2012.84 · Cited by 39 · see citing works
Combining Customer Attribute and Social Network Mining for Prepaid Mobile Churn Prediction
Kusuma, P. D., Takes, F. W., & van der Putten, P. (2013) · Cited by 19 · see citing works
Recommendation method for extending subscription periods
Iwata, T., Saito, K., & Yamada, T. (2006) · ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/1150402.1150470 · Cited by 15 · see citing works
Flagged first, then by citations
Research works printed but not linked: 2
- idate, 0, Markets and Trends 2012-2016 Market Research Report
- hadden, 2006, Chum Prediction using complaints data, Enforratika, 13
Cited by
Sorted by citations
Predicting player churn in the wild
Hadiji, F., Sifa, R., Drachen, A., Thurau, C., Kersting, K., & Bauckhage, C. (2014) · 2014 IEEE Conference on Computational Intelligence and Games · doi:10.1109/cig.2014.6932876 · Cited by 154 · see citing works
A Survey on Churn Analysis in Various Business Domains
Ahn, J., Hwang, J., Kim, D., Choi, H., & Kang, S. (2020) · IEEE Access · doi:10.1109/access.2020.3042657 · Cited by 108 · see citing works
“Thus, the AUC close to 1 indicates that the churn prediction model accurately distinguishes difference between the characteristics of churn customers and non-churn customers [13], [45], [55], [95].”
BackgroundInfluential
- Authors
- Runge, J., Gao, P., Garcin, F., & Faltings, B.
- Affiliations
- École Polytechnique Fédérale de Lausanne (CH)
- Venue
- 2014 IEEE Conference on Computational Intelligence and Games
- Publisher
- IEEE
- Published
- 2014-08
- Pages
- 1-8
- OpenAlex
- W2087097402
- Semantic Scholar
- fc226cef2a2ecc08767cb7dfde807c5fc4dd7304
- Cited by
- 144
- References
- 15
- Citations by year
- 2026: 3 · 2025: 9 · 2024: 7 · 2023: 3 · 2022: 13 · 2021: 16 · 2020: 15 · 2019: 17 · 2018: 23 · 2017: 13 · 2016: 13 · 2015: 10 · 2014: 2
- FWCI
- 52.14
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Conference on Computational Intelligence and Games (CIG) (publishedVersion)
- Topics
- Social Sciences › Business, Management and Accounting › Marketing › Customer churn and segmentation
- Physical Sciences › Computer Science › Computer Science Applications › Online Learning and Analytics
- Social Sciences › Business, Management and Accounting › Organizational Behavior and Human Resource Management › AI and HR Technologies
- Keywords
- player retention, hidden Markov models, artificial neural networks, machine learning classifiers, A/B testing, crosslinking, in-game advertising, game monetization, temporal dynamics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
