Published December 26, 2022 | Version 01
Journal article Open

Customer Churn Prediction Using Machine Learning Techniques: the case of Lion Insurance

Creators

  • 1. Addis Ababa Science and Technology University, Addis Ababa, Ethiopia.

Contributors

  • 1. Addis Ababa Science and Technology University, Addis Ababa, Ethiopia

Description

The growth of an insurance company is measured by the number of policies purchased by customers. To keep the company growing and having more customers, the customer churn prediction model is crucial to maintain its competitiveness. Even if the company has good service delivery, it is important to identify the customer’s behavior and be able to predict the future churners. The main contribution to our work is the development of a predictive model that can proactively predict the customer who will leave the insurance company. The model developed in this study uses machine learning techniques on lion insurance data. Another main contribution of this study is the labeling of the data using an unsupervised algorithm on 12007 rows with 9 features from which 2 clusters were generated using the K-means++ algorithm. As the cluster results found are imbalanced, the synthetic minority oversampling technique was applied to the training dataset. The Deep Neural Network algorithm turns out to be a very effective model for predicting customer churn, reaching an accuracy of 98.81%. The two years of customer data were obtained from lion insurance and used to train test, and evaluate the model. The Randomized optimization technique was selected for each algorithm. However, the best results were obtained by a deep neural network with a structure of (9-55-55-55-55-55-1). This algorithm was selected for classification in this churn prediction study.

Files

74687.pdf

Files (410.0 kB)

Name Size Download all
md5:52e8551f2b11a91d858deee9f37874e9
410.0 kB Preview Download

Additional details

References

  • [1] Insurance Information Institute, Insurance Handbook- An insurance guide: what it does and how it works. 2010.
  • [2] S. R. Corporate, A History of Insurance in Japan, p. 4, 2017, [Online]. Available: www.swissre.com.
  • [3] D. J. Kuss, M. D. Griffiths, J. F. Binder, and B. Street, Metadata, citation and similar papers at core.ac.uk, pp. 1–19, 2013.
  • [4] I. Institutions and O. In, Insurance Companies Name & Address. 2012.
  • [5] Yitagesu kebede, establishment of lion insurance, 2007. https://www.anbessainsurance.com/profile.php.
  • [6] M. Harris and H. J. Harrington, Service Quality in the Knowledge Age, Measuring Business Excellence, vol. 4, no. 4, pp. 31–36, Jan. 2000, doi: 10.1108/13683040010362562.
  • [7] P. E. Pfeifer, The optimal ratio of acquisition, Journal of Targeting, Measurement & Analysis for Marketing, vol. 13, no. 2, pp. 179–188, 2005.
  • [8] M. Negash, K. Venugopal, and S. Asmare, Identifying and Analyzing of Factors Contributing for Growth of Non–Life Insurance Gross Premium a Developing Country Perspective: Case of Insurance Industry in Ethiopia, SSRN Electronic Journal, Jan. 2018, doi: 10.2139/ssrn.3430324.
  • [9] A. Punoo, M. Otta, M. Fayaz, and S. Abdul Khader, Machine Learning in Insurance. 2022.
  • [10] D. R. Biggar, Competition and Related Regulation Issues in the Insurance Industry, SSRN Electronic Journal, vol. I, no. June, 2005, DOI: 10.2139/ssrn.185068.
  • [11] I. El Naqa and M. Murphy, What Is Machine Learning?, 2015, pp. 3–11.
  • [12] Thomas H. Davenport, What are some popular machine learning methods?, 2019. https://www.sas.com/ en_us/insights/analytics/machine-learning.html.
  • [13] Quantilus, Machine Learning Important and How will it Impact Business?, 2020. https://quantilus.com/ why-is-machine-learning-important-and-how-will-it-impact-business/.
  • [14] V. Bhambri and I. Research Scholar, Singhania University, Pacheri Bari, Jhunjhunu, Rajasthan, Data Mining as a Tool to Predict Churn Behavior of Customers, vol. 2, pp. 85–89, 2012.
  • [15] G. Nie, W. Rowe, L. Zhang, Y. Tian, and Y. Shi, Credit card churn forecasting by logistic regression and decision tree, Expert Systems with Applications, vol. 38, no. 12, pp. 15273–15285, 2011.
  • [16] A. Sharma and P. Kumar Panigrahi, A Neural Network based Approach for Predicting Customer Churn in Cellular Network Services, International Journal of Computer Applications, vol. 27, no. 11, pp. 26–31, 2011.
  • [17] C. Huigevoort, Customer churn prediction for an insurance company, no. April, p. 99, 2015.
  • [18] A. Ayache, M. Calciu, M. Fradon, and F. Salerno, Analytic solution to find optimal balance between customer acquisition and retention spending. Solution analytique pour trouver le meilleur équilibre entre les dépenses d'acquisition et rétention de clientèle.
  • [19] S. Vluymans, Multi-label Learning, Studies in Computational Intelligence, vol. 807, pp. 189–218, 2019, DOI: 10.1007/978-3-030-04663-7_7.
  • [20] T.Kamalakannan, P.Mayilvahanan Efficient Customer Churn Prediction Model Using Support Vector Machine with Particle Swarm Optimization, International Journal of Pure and Applied Mathematics, vol. 119, no. 10, pp. 247–254, 2018.
  • [21] M. Spiteri and G. Azzopardi, Customer churn prediction for a motor insurance company, 2018 13th International Conference on Digital Information Management, ICDIM 2018, 2018, pp. 173–178, 2018.
  • [22] C. Bellani, Predictive Churn Models in Vehicle Insurance, 2019, [Online]. Available: http://hdl.handle.net/ 10362/90767.
  • [23] M. R. Ismail, M. K. Awang, M. N. A. Rahman, and M. Makhtar, A multi-layer perceptron approach for customer churn prediction, International Journal of Multimedia and Ubiquitous Engineering, vol. 10, no. 7, pp. 213–222, 2015, DOI: 10.14257/ijmue.2015.10.7.22.
  • [24] O. A and A. A. B, Customer Churn Analysis In Banking Sector Using Data Mining Techniques, African Journal of Computing & ICT, vol. 8, no. 3, pp. 165–174, 2015.
  • [25] I. Franciska and B. Swaminathan, Churn prediction analysis using various clustering algorithms in KNIME analytics platform, Proceedings of 2017 3rd IEEE International Conference on Sensing, Signal Processing and Security, ICSSS 2017, pp. 166–170, 2017, DOI: 10.1109/SSPS.2017.8071585.
  • [26] J. Kamiri and G. Mariga, Research Methods in Machine Learning: A Content Analysis, International Journal of Computer and Information Technology(2279-0764), vol. 10, pp. 764–2279, Mar. 2021.
  • [27] S. B. Kotsiantis and D. Kanellopoulos, Data preprocessing for supervised leaning, vol. 1, no. 2, pp. 1–7, 2006.
  • [28] M. R. Khan, J. Manoj, A. Singh, and J. E. Blumenstock, Behavioral Modeling for Churn Prediction: Early Indicators and Accurate Predictors of Custom Defection and Loyalty, 2015 IEEE International Congress on Big Data, pp. 677–680, 2015.
  • [29] D. Elreedy and A. F. Atiya, A comprehensive analysis of synthetic minority oversampling technique (SMOTE) for handling class imbalance, Information Sciences, vol. 505, pp. 32–64, 2019.