Predicting Player Churn with Echo State Networks

We introduce the idea of utilizing a recurrent neural network based representation learning approach to extract and model the complex and sequentially dependent player behavior in games. Our approach is based on the dynamical systems of Echo State Networks, which are very simple to evaluate yet powerful temporal representation learners. We empirically evaluate our approach by illustrating a case study for predicting player churn.

[1]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[2]  Christian Bauckhage,et al.  Predicting Purchase Decisions in Mobile Free-to-Play Games , 2015, AIIDE.

[3]  Fabio Zambetta,et al.  Predicting player churn in destiny: A Hidden Markov models approach to predicting player departure in a major online game , 2016, 2016 IEEE Conference on Computational Intelligence and Games (CIG).

[4]  Boi Faltings,et al.  Hidden Markov models for churn prediction , 2015, 2015 SAI Intelligent Systems Conference (IntelliSys).

[5]  Hossam Faris,et al.  Echo State Network with SVM-readout for customer churn prediction , 2015, 2015 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT).

[6]  Sam Devlin,et al.  Predicting player disengagement and first purchase with event-frequency based data representation , 2015, 2015 IEEE Conference on Computational Intelligence and Games (CIG).

[7]  Xi Liu,et al.  A Semi-Supervised and Inductive Embedding Model for Churn Prediction of Large-Scale Mobile Games , 2018, 2018 IEEE International Conference on Data Mining (ICDM).

[8]  Rajkumar Ramamurthy,et al.  Matrix- and Tensor Factorization for Game Content Recommendation , 2019, KI - Künstliche Intelligenz.

[9]  Christian Bauckhage,et al.  Echo State Networks for Named Entity Recognition , 2019, ICANN.

[10]  Paolo Burelli.  Predicting Customer Lifetime Value in Free-to-Play Games , 2019, Data Analytics Applications in Gaming and Entertainment.

[11]  Christian Bauckhage,et al.  The Playtime Principle: Large-scale cross-games interest modeling , 2014, 2014 IEEE Conference on Computational Intelligence and Games.

[12]  Wonjong Rhee,et al.  Churn prediction of mobile and online casual games using play log data , 2017, PloS one.

[13]  Peng Gao,et al.  Churn prediction for high-value players in casual social games , 2014, 2014 IEEE Conference on Computational Intelligence and Games.

[14]  Zehong Yang,et al.  Short-term stock price prediction based on echo state networks , 2009, Expert Syst. Appl..

[15]  Christian Bauckhage,et al.  Customer Lifetime Value Prediction in Non-Contractual Freemium Settings: Chasing High-Value Users Using Deep Neural Networks and SMOTE , 2018, HICSS.

[16]  Jukka Heikkonen,et al.  User activity decay in mobile games determined by simple differential equations? , 2016, 2016 IEEE Conference on Computational Intelligence and Games (CIG).

[17]  Daniel Paurat,et al.  Simple Recurrent Neural Networks for Support Vector Machine Training , 2018, ICANN.

[18]  Kathryn Kasmarik,et al.  Weekly Seasonal Player Population Patterns in Online Games: A Time Series Clustering Approach , 2019, 2019 IEEE Conference on Games (CoG).

[19]  Douwe Kiela,et al.  No Training Required: Exploring Random Encoders for Sentence Classification , 2019, ICLR.

[20]  Anna Guitart,et al.  Churn Prediction in Mobile Social Games: Towards a Complete Assessment Using Survival Ensembles , 2016, 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[21]  Christian Bauckhage,et al.  Predicting Retention in Sandbox Games with Tensor Factorization-based Representation Learning , 2016, 2016 IEEE Conference on Computational Intelligence and Games (CIG).

[22]  Claudio Gallicchio,et al.  Deep Echo State Networks for Diagnosis of Parkinson's Disease , 2018, ESANN.

[23]  Yuan Cao,et al.  Echo State Neural Machine Translation , 2020, ArXiv.

[24]  Diego Klabjan,et al.  Retention Prediction in Sandbox Games with Bipartite Tensor Factorization , 2020, SAI.

[25]  Diego Klabjan,et al.  To be or not to be...social: incorporating simple social features in mobile game customer lifetime value predictions , 2018, ACSW.

[26]  Alain Saas,et al.  Discovering playing patterns: Time series clustering of free-to-play game data , 2016, 2016 IEEE Conference on Computational Intelligence and Games (CIG).

[27]  Karsten Rothmeier,et al.  Prediction of Player Churn and Disengagement Based on User Activity Data of a Freemium Online Strategy Game , 2020, IEEE Transactions on Games.

[28]  Paolo Burelli,et al.  Combining Sequential and Aggregated Data for Churn Prediction in Casual Freemium Games , 2019, 2019 IEEE Conference on Games (CoG).

[29]  Christian Bauckhage,et al.  Predicting player churn in the wild , 2014, 2014 IEEE Conference on Computational Intelligence and Games.