A Trajectory-based Deep Sequential Method for Customer Churn Prediction

Customer churn prediction is a pivotal issue in business marketing. Many researches have been pursuing more efficient features and techniques for it. Rapid growth of mobile Internet devices has generated large amounts of customer trajectory data, which contains abundant customer behavior patterns and contributes to many business actions. In this paper we propose a trajectory-based deep sequential method called TR-LSTM for customer churn prediction to mining the customer behavior pattern behind trajectory data. The method extracts three types of trajectory-based features and applied the long short-term memory neural network (LSTM) to conduct sequential modeling. Experimental results on real-world customer trajectory data sets demonstrate that the proposed TR-LSTM obtains better performance than all baseline methods. Our method provides a new tool of churn prediction for both academics and practitioners.

[1]  Jaideep Srivastava,et al.  Churn Prediction in MMORPGs: A Social Influence Based Approach , 2009, 2009 International Conference on Computational Science and Engineering.

[2]  Yu Zheng,et al.  Trajectory Data Mining , 2015, ACM Trans. Intell. Syst. Technol..

[3]  Jiri Matas,et al.  Systematic evaluation of convolution neural network advances on the Imagenet , 2017, Comput. Vis. Image Underst..

[4]  João Falcão e Cunha,et al.  Modeling partial customer churn: On the value of first product-category purchase sequences , 2012, Expert systems with applications.

[5]  Guangquan Zhang,et al.  A Customer Churn Prediction Model in Telecom Industry Using Boosting , 2014, IEEE Transactions on Industrial Informatics.

[6]  Burcin Bozkaya,et al.  Money Walks: Implicit Mobility Behavior and Financial Well-Being , 2015, PloS one.

[7]  Li Hong,et al.  Predicting Customer Churn in Mobile Telephony Industry Using Probabilistic Classifiers in Data Mining , 2013 .

[8]  A. Karpatne,et al.  Spatio-Temporal Data Mining: A Survey of Problems and Methods , 2017, ArXiv.

[9]  Özden Gür Ali,et al.  Dynamic churn prediction framework with more effective use of rare event data: The case of private banking , 2014, Expert Syst. Appl..

[10]  Natwar Modani,et al.  CDR Analysis Based Telco Churn Prediction and Customer Behavior Insights: A Case Study , 2013, WISE.

[11]  Anna Monreale,et al.  WhereNext: a location predictor on trajectory pattern mining , 2009, KDD.

[12]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[13]  P. Danaher,et al.  Implementing a customer relationship strategy: The asymmetric impact of poor versus excellent execution , 2000 .

[14]  Anindya Ghose,et al.  Mobile Targeting Using Customer Trajectory Patterns , 2019, Manag. Sci..

[15]  Philip Spanoudes,et al.  Deep Learning in Customer Churn Prediction: Unsupervised Feature Learning on Abstract Company Independent Feature Vectors , 2017, ArXiv.

[16]  K. Iyakutti,et al.  Automated Feature Selection and Churn Prediction using Deep Learning Models , 2017 .

[17]  Guo-en Xia,et al.  Model of Customer Churn Prediction on Support Vector Machine , 2008 .

[18]  Yao Zhao,et al.  Learning Heterogeneous Spatial-Temporal Representation for Bike-Sharing Demand Prediction , 2019, AAAI.

[19]  Stefan Lessmann,et al.  Incorporating textual information in customer churn prediction models based on a convolutional neural network , 2019 .

[20]  J. R. Bult,et al.  Optimal Selection for Direct Mail , 1995 .

[21]  Hal Daumé,et al.  Short Text Representation for Detecting Churn in Microblogs , 2016, AAAI.

[22]  Wagner A. Kamakura,et al.  Defection Detection: Measuring and Understanding the Predictive Accuracy of Customer Churn Models , 2006 .