International Journal of Modern Education and Computer Science (IJMECS)
IJMECS Vol. 11, No. 6, 8 Jun. 2019
Cover page and Table of Contents: PDF (size: 904KB)
Combined Appetency and Upselling Prediction Scheme in Telecommunication Sector Using Support Vector Machines
Full Text (PDF, 904KB), PP.1-7
Views: 0 Downloads: 0
Author(s)
Lian-Ying Zhou
1,*
Daniel M. Amoh
2
Louis K. Boateng
2
Andrews A. Okine
2
Index Terms
Customer Relations Management, Telecommunication, Churn prediction, Appetency prediction, Up-selling prediction, Support Vector Machines, classification.
Abstract
Customer Relations Management (CRM) is an essential marketing approach which telecommunication companies use to interact with current and prospective customers. In recent years, researchers and practitioners have investigated customer churn prediction (CCP) as a CRM approach to differentiate churn from non-churn customers. CCP helps businesses to design better retention measures to retain and attract customers. However, a review of the telecommunication sector revealed little to no research works on appetency (i.e. customers likely to purchase new product) and up-selling (i.e. customers likely to buy upgrades) customers. In this paper, a novel up-selling and appetency prediction scheme is presented based on support vector machine (SVM) algorithm using linear and polynomial kernel functions. This study also investigated how using different sample sizes (i.e. training to test sets) impacted the classification performance. Our findings demonstrated that the polynomial kernel function obtained the highest accuracy and the least minimum error in the first three sample sizes (i.e. 80:20, 77:23, 75:25) %. The proposed model is effective in predicting appetency and up-sell customers from a publicly available dataset.
Cite This Paper
Lian-Ying Zhou, Daniel M. Amoh, Louis K. Boateng, Andrews A. Okine, "Combined Appetency and Upselling Prediction Scheme in Telecommunication Sector Using Support Vector Machines", International Journal of Modern Education and Computer Science(IJMECS), Vol.11, No.6, pp. 1-7, 2019.DOI: 10.5815/ijmecs.2019.06.01
Reference
[1]Xia, G.-e. and W.-d. Jin, Model of Customer Churn Prediction on Support Vector Machine. Systems Engineering - Theory & Practice, 2008. 28(1): p. 71-77.
[2]Amin, A., et al., Customer churn prediction in the telecommunication sector using a rough set approach. Neurocomputing, 2017. 237: p. 242-254.
[3]Rodan, A., et al., A Support Vector Machine Approach for Churn Prediction in Telecom Industry. Vol. 17. 2014.
[4]Ionut Brandusoiu, G.T., Churn Prediction in the Telecommunications Sector using Support Vector machines. Annals of the University of Oradea, 2013. Volume xxii (xii), 2013/1.
[5]Ahmed, A. and D. Maheswari Linen, A review and analysis of churn prediction methods for customer retention in telecom industries. 2017. 1-7.
[6]Bloemer, J., K. de Ruyter, and P. Peeters, Investigating drivers of bank loyalty: the complex relationship between image, service quality and satisfaction. 1998. 16(7): p. 276-286.
[7]De Caigny, A., K. Coussement, and K. De Bock, A New Hybrid Classification Algorithm for Customer Churn Prediction Based on Logistic Regression and Decision Trees. Vol. 269. 2018.
[8]Vapnik, V.N., The nature of statistical learning theory. 1995: Springer-Verlag. 188.
[9]Coussement, K. and D. Van den Poel, Churn prediction in subscription services: An application of support vector machines while comparing two parameter-selection techniques. Expert Systems with Applications, 2008. 34(1): p. 313-327.
[10]V. Umayaparvathi, K.I., A Survey on Customer Churn Prediction in Telecom Industry: Datasets, Methods and Metrics. International Research Journal of Engineering and Technology (IRJET), 2016. 03(04).
[11]Gordini, N. and V. Veglio, Customers churn prediction and marketing retention strategies. An application of support vector machines based on the AUC parameter-selection technique in B2B e-commerce industry. Industrial Marketing Management, 2017. 62: p. 100-107.
[12]Fletcher, T., Support Vector Machines Explained. 2009.
[13]R. Berwick, V.I., An Idiot’s guide to Support vector machines (SVMs) 2003.
[14]Ng, A., CS229 Lecture notes. 2000.
[15]Noble, W.S., What is a support vector machine? Nature Biotechnology, 2006. 24: p. 1565.
[16]Hsu, C., C. Chang, and C. Lin, A practical guide to support vector classification. Vol. 101. 2008. 1396-1400.
[17]Duan, K., et al., Multi-Category Classification by Soft-Max Combination of Binary Classifiers. 2003. 125-134.
[18]Qing, T., et al., Posterior probability support vector Machines for unbalanced data. IEEE Transactions on Neural Networks, 2005. 16(6): p. 1561-1573.
[19]Platt, J., Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods. Vol. 10. 2000.
[20]Becks, D. Churn in Telecom's dataset. 2018 [cited 2019 25]; Available from: https://www.kaggle.com/becksddf/churn-in-telecoms-dataset/version/1.
[21]Stojanović, M.B., et al., A methodology for training set instance selection using mutual information in time series prediction. Neurocomputing, 2014. 141: p. 236-245.
[22]Malik, Z.K., A. Hussain, and J. Wu, An online generalized eigenvalue version of Laplacian Eigenmaps for visual big data. Neurocomputing, 2016. 173: p. 127-136.
[23]Dr. M. Balasubramanian , M.S., Churn Prediction in Mobile Telecom System using Data Mining Techniques International Journal Of Scientific And Research Publilcations, 2014. 4(4).
[24]Bellazzi, R. and B. Zupan, Predictive data mining in clinical medicine: current issues and guidelines. Int J Med Inform, 2008. 77(2): p. 81-97.