pRNN: A Recurrent Neural Network based Approach for Customer Churn Prediction in Telecommunication Sector

Predicting churning customers in advance allows marketers to retain existing and valuable customers, and to develop a customer churn predicting model is a key issue of customer relationship management in modern marketing. In this paper, a product-based Recurrent Neural Network (pRNN) approach is proposed for customer churn prediction in telecommunication sector. In the proposed model, RNN with long short-term memory units is used to learn sequential patterns from customer data changing over time, and the product operation is introduced before recurrent layer to learn high-order interaction between features. pRNN is applied on a real-world telecommunication dataset; experiment results demonstrate that pRNN significantly outperforms other comparison models.

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

[2]  Xiangang Li,et al.  Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition , 2014, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

[4]  Wang Jun,et al.  Product-Based Neural Networks for User Response Prediction , 2016 .

[5]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[6]  Federico Castanedo,et al.  Using Deep Learning to Predict Customer Churn in a Mobile Telecommunication Network , 2014 .

[7]  Zheng Hu,et al.  Not Too Late to Identify Potential Churners: Early Churn Prediction in Telecommunication Industry , 2016, 2016 IEEE/ACM 3rd International Conference on Big Data Computing Applications and Technologies (BDCAT).

[8]  Bart Baesens,et al.  A Novel Profit Maximizing Metric for Measuring Classification Performance of Customer Churn Prediction Models , 2013, IEEE Transactions on Knowledge and Data Engineering.

[9]  Kyoungok Kim,et al.  Sequential manifold learning for efficient churn prediction , 2012, Expert Syst. Appl..

[10]  Annisa Aditsania,et al.  Using Deep Learning To Predict Customer Churn In A Mobile Telecomunication Network , 2016 .

[11]  Jürgen Schmidhuber,et al.  Learning to forget: continual prediction with LSTM , 1999 .

[12]  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).

[13]  Farhan Khan,et al.  Sequential churn prediction and analysis of cellular network users — A multi-class, multi-label perspective , 2017, 2017 25th Signal Processing and Communications Applications Conference (SIU).

[14]  Andrew W. Senior,et al.  Long short-term memory recurrent neural network architectures for large scale acoustic modeling , 2014, INTERSPEECH.

[15]  João Falcão e Cunha,et al.  Predicting partial customer churn using Markov for discrimination for modeling first purchase sequences , 2012, Adv. Data Anal. Classif..

[16]  Kristof Coussement,et al.  Faculteit Economie En Bedrijfskunde Hoveniersberg 24 B-9000 Gent Churn Prediction in Subscription Services: an Application of Support Vector Machines While Comparing Two Parameter-selection Techniques Churn Prediction in Subscription Services: an Application of Support Vector Machines While Comparin , 2022 .

[17]  Eric W. T. Ngai,et al.  Customer churn prediction using improved balanced random forests , 2009, Expert Syst. Appl..

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

[19]  Hongxia Jin,et al.  Disguise Adversarial Networks for Click-through Rate Prediction , 2017, IJCAI.