Deep Convolutional Neural Networks for Customer Churn Prediction Analysis

Several machine learning models have been proposed to address customer churn problems. In this work, the authors used a novel method by applying deep convolutional neural networks on a labeled dataset of 18,000 prepaid subscribers to classify/identify customer churn. The learning technique was based on call detail records (CDR) describing customers activity during two-month traffic from a real telecommunication provider. The authors use this method to identify new business use case by considering each subscriber as a single input image describing the churning state. Different experiments were performed to evaluate the performance of the method. The authors found that deep convolutional neural networks (DCNN) outperformed other traditional machine learning algorithms (support vector machines, random forest, and gradient boosting classifier) with F1 score of 91%. Thus, the use of this approach can reduce the cost related to customer loss and fits better the churn prediction business use case.

[1]  Chih-Fong Tsai,et al.  Customer churn prediction by hybrid neural networks , 2009, Expert Syst. Appl..

[2]  M. Tahar Kechadi,et al.  Customer churn prediction in telecommunications , 2012, Expert Syst. Appl..

[3]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Alae Chouiekh,et al.  Machine learning techniques applied to prepaid subscribers: Case study on the telecom industry of Morocco , 2017, International Symposium on Computer Vision.

[5]  Marcin Owczarczuk,et al.  Churn models for prepaid customers in the cellular telecommunication industry using large data marts , 2010, Expert Syst. Appl..

[6]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[7]  Xiang Zhang,et al.  Character-level Convolutional Networks for Text Classification , 2015, NIPS.

[8]  Hüseyin Uzunalioglu,et al.  Prediction of subscriber churn using social network analysis , 2013, Bell Labs Technical Journal.

[9]  Koen W. De Bock,et al.  An empirical evaluation of rotation-based ensemble classifiers for customer churn prediction , 2011, Expert Syst. Appl..

[10]  Y. Ilker Topcu,et al.  Applying Bayesian Belief Network approach to customer churn analysis: A case study on the telecom industry of Turkey , 2011, Expert Syst. Appl..

[11]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[12]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Tetsuya Ogata,et al.  Audio-visual speech recognition using deep learning , 2014, Applied Intelligence.

[14]  Kaizhu Huang,et al.  Customer churn prediction in the telecommunication sector using a rough set approach , 2017, Neurocomputing.

[15]  Razvan Pascanu,et al.  Advances in optimizing recurrent networks , 2012, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[16]  Johannes Stallkamp,et al.  The German Traffic Sign Recognition Benchmark: A multi-class classification competition , 2011, The 2011 International Joint Conference on Neural Networks.

[17]  Luo Bin,et al.  Customer Churn Prediction Based on the Decision Tree in Personal Handyphone System Service , 2007, 2007 International Conference on Service Systems and Service Management.

[18]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

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

[20]  A. Buja,et al.  Loss Functions for Binary Class Probability Estimation and Classification: Structure and Applications , 2005 .

[21]  Mohak Shah,et al.  Comparative Study of Caffe, Neon, Theano, and Torch for Deep Learning , 2015, ArXiv.

[22]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

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

[24]  Asifullah Khan,et al.  Churn prediction in telecom using Random Forest and PSO based data balancing in combination with various feature selection strategies , 2012, Comput. Electr. Eng..

[25]  Asifullah Khan,et al.  Intelligent churn prediction in telecom: employing mRMR feature selection and RotBoost based ensemble classification , 2013, Applied Intelligence.

[26]  M. Tahar Kechadi,et al.  A new feature set with new window techniques for customer churn prediction in land-line telecommunications , 2010, Expert Syst. Appl..

[27]  Xin Yao,et al.  A novel evolutionary data mining algorithm with applications to churn prediction , 2003, IEEE Trans. Evol. Comput..

[28]  Abbas Keramati,et al.  Improved churn prediction in telecommunication industry using data mining techniques , 2014, Appl. Soft Comput..

[29]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[30]  Xiaoli Li,et al.  Deep Convolutional Neural Networks on Multichannel Time Series for Human Activity Recognition , 2015, IJCAI.

[31]  Konstantinos I. Diamantaras,et al.  A comparison of machine learning techniques for customer churn prediction , 2015, Simul. Model. Pract. Theory.

[32]  Minghe Sun,et al.  A hierarchical multiple kernel support vector machine for customer churn prediction using longitudinal behavioral data , 2012, Eur. J. Oper. Res..

[33]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[34]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[35]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.