Performance Comparison of Neural Network Training Algorithms for Modeling Customer Churn Prediction

  • Authors

    • Mohd Khalid Awang
    • Mohammad Ridwan Ismail
    • Mokhairi Makhtar
    • M Nordin A Rahman
    • Abd Rasid Mamat
    2018-04-06
    https://doi.org/10.14419/ijet.v7i2.15.11196
  • Neural Network Learning Algorithm, Data Mining, Customer Churn Prediction, Multilayer Perceptron
  • Predicting customer churn has become the priority of every telecommunication service provider as the market  is becoming more saturated and competitive. This paper presents a comparison of neural network learning algorithms for customer churn prediction.  The data set used to train and test the neural network algorithms was provided by one of the leading telecommunication company in Malaysia. The Multilayer Perceptron (MLP) networks are trained using nine (9) types of learning algorithms, which are Levenberg Marquardt backpropagation (trainlm), BFGS Quasi-Newton backpropagation (trainbfg), Conjugate Gradient backpropagation with Fletcher-Reeves Updates (traincgf), Conjugate Gradient backpropagation with Polak-Ribiere Updates (traincgp), Conjugate Gradient backpropagation with Powell-Beale Restarts (traincgb), Scaled Conjugate Gradient backpropagation (trainscg), One Step Secant backpropagation (trainoss), Bayesian Regularization backpropagation (trainbr), and Resilient backpropagation (trainrp). The performance of the Neural Network is measured based on the prediction accuracy of the learning and testing phases. LM learning algorithm is found to be the optimum model of a neural network model consisting of fourteen input units, one hidden node and one output node. The best result of the experiment indicated that this model is able to produce the performance accuracy of 94.82%.

     

  • References

    1. [1] S. Portelaa and R. Menezes, Modeling Customer Churn: An Application of Duration Models. Proceedings of the Australian and New Zealand Marketing Academy (ANZMAC) (2009)

      [2] J. Hadden, A Customer Profiling Methodology for Churn Prediction. Cranfield University (2008)

      [3] A. Sharma and P. K. Panigrahi, A Neural Network based Approach for Predicting Customer Churn in Cellular Network Services. International Journal of Computer Applications, (2011) 27(11), 26-31

      [4] H. E. Chueh, Analysis of marketing data to extract key factors of telecom churn management. African Journal of Business Management, (2011) 5(20), 8242-8247

      [5] A. Berson, S. J. Smith and K. Thearling, Building Data Mining Applications for CRM, McGraw-Hill, NewYork (2000)

      [6] M. C. Mozer, R. Wolniewicz, D.B. Grimes, E. Johnson and H. Kaushansky, Predicting Subscriber Dissatisfaction and Improving Retention in the Wireless Telecommunications Industry. IEEE Transactions On Neural Networks, (2000) 11(3), 690 - 696.

      [7] B. H. Chu, M.S. Tsai and C.S. Ho, Toward a hybrid data mining model for customer retention. Knowledge-Based Systems, (2007) 20(8), 703-718.

      [8] M.K. Awang, M.N.A. Rahman and M.R. Ismail, Data Mining for Churn Prediction: Multiple Regressions Approach, Computer Applications for Database, Education, and Ubiquitous Computing. Springer Berlin Heidelberg, (2012) 318-324

      [9] D. Chiang, Y. Wang, S. Lee and C. Lin, Goal-oriented sequential pattern for network banking and churn analysis. Expert systems with applications, (2003) 25, 293-302.

      [10] A. T. Kearney, European Mobile Industry Observatory 2011. In GSMA (Ed.), Rising to the Challenge of Intense Competition, (2011)

      [11] A. D. Athanassopoulos, Customer Satisfaction Cues To Support Market Segmentation and Explain Switching Behavior. Journal of Business Research, , (2000) 47, 191-207

      [12] S.K. Abi, M.R. Gholamian, M. R. and M. Namvar, Data Mining Applications in Customer Churn Management. Paper presented at the International Conference on Intelligent Systems, Modelling and Simulation, (2010)

      [13] J. B. Ferreira, M. Vellasco,M. A. Pacheco and C. H. Barbosa, Data Mining Techniques on the Evaluation of Wireless Churn. Paper presented at the European Symposium on Artificial Neural Networks (2004)

      [14] Y. He, Z. He and D. Zhang, A Study on Prediction of Customer Churn in Fixed Communication Network Based on Data Mining. Paper presented at the Sixth International Conference on Fuzzy Systems and Knowledge Discovery (2009)

      [15] P. Datta, B. Masand, D. R. Mani and B. Li, Automated Cellular Modeling and Prediction on a Large Scale. Artificial Intelligence Review, (2000) 14(6), 485-502

      [16] C. Kang and S. Pei-ji, Customer Churn Prediction Based on SVM-RFE. Paper presented at the International Seminar on Business and Information Management, (2008)

      [17] S. Haykin, Neural Network : A Comparehsive Foundation (Vol. 2). New Jersey Prentice Hall International, (1999 )

      [18] A. Krogh, What are artificial neural networks? Nature Publishing Group, (2008) 26(2), 195-197

      [19] D. M. Levine, P. P. Ramsey and R. K. Smidt, Applied statistics for engineers and scientists: using Microsoft Excel and Minitab. Upper Saddle River, NJ: Prentice Hall, (2001)

      [20] S. A. Sweet and K. Grace-Martin, Data Analysis with SPSS: A First Course in Applied Statistics (Vol. 2), Pearson (2010)

      [21] L. Fausett, Fundamentals of neural networks: architectures, algorithms, and applications. (1994)

  • Downloads

  • How to Cite

    Khalid Awang, M., Ridwan Ismail, M., Makhtar, M., Nordin A Rahman, M., & Rasid Mamat, A. (2018). Performance Comparison of Neural Network Training Algorithms for Modeling Customer Churn Prediction. International Journal of Engineering & Technology, 7(2.15), 35-37. https://doi.org/10.14419/ijet.v7i2.15.11196