Maintaining customer lifetime value through cross selling offers with shopping vouchers gimmick in the insurance industry by using logistic regression and decision tree
##plugins.themes.academic_pro.article.sidebar##
Downloads
##plugins.themes.academic_pro.article.main##
Abstract
This research is conducted in the life insurance industry in order to help the company to extend and maintain customer lifetime value. A statistical model will be built using Logistic Regression (LR) and Decision Tree (DT) methods so that the company can find/use the right model of input variables (independent variables) those later determines/increases the probability/chance of the take up rate of the cross-selling offers: whether YES (accept the given offer) or NO (reject the given offer). The impact of shopping vouchers as gimmick will be seen as well. This research is using primary data in the form of data of active life insurance policyholders who currently have a term life product where the policy is approaching the maturity date (3 months before the maturity date). Policyholders, hereinafter referred to as clients, consist of custo500 clients with the following demographic profiles: Gender: Male/Female; Age: 45-60 years, Marital Status: Single, Married, Divorced; Have made a claim: Yes/No, Policy Age: 5, 10 and 15 years, Annual Premium Value: 20 - 54 Million; Communication Channels in distributing the offer: SMS, Email, Mail (specifically Mail: only given to clients over 55 years of age); The rupiah value of the vouchers offered: IDR 250k, 350k and 500k. The data was obtained from the results of cross sell activities carried out by the company from one of the cross-sell initiative batches. The statistical model will be built using the logistic regression and decision tree method with Visual Studio Code - Python software. Responds to offers in the form of Yes or No are withdrawn after 30 calendar days after the offer is made. From the results of the research, the Logistic Regression model give result with Accuracy: 0.95; Precision: 0.75; Recall: 0.66 and F1-score: 0.70. The Decision Tree model give result with Accuracy: 0.93; Precision: 0.84; Recall: 0.81 and F1-score: 0.69. The two models provide almost similar performance. Novelty of this research shows claims experience play dominant role in determining the result of the cross sell on top of the voucher gimmick offer
##plugins.themes.academic_pro.article.details##
References
Brankovic, L. (2005). DETECTIVE: A Decision Tree Based Categorical Value Clustering and Perturbation Technique for Preserving Privacy in Data Mining.
De Caigny, A., Coussement, K., & De Bock, K. W. (2018). A new hybrid classification algorithm for customer churn prediction based on logistic regression and decision trees. European Journal of Operational Research, 269(2), 760–772. https://doi.org/10.1016/j.ejor.2018.02.009
Elyusufi, M’hamed, Y., & Kbir, A. (n.d.). Churn Prediction Analysis by Combining Machine Learning Algorithms and Best Features Exploration. In IJACSA) International Journal of Advanced Computer Science and Applications (Vol. 13, Issue 7). www.ijacsa.thesai.org
Fiskin, R., Cakir, E., & Sevgili, C. (2021). Decision Tree and Logistic Regression Analysis to Explore Factors Contributing to Harbour Tugboat Accidents. Journal of Navigation, 74(1), 79–104. https://doi.org/10.1017/S0373463320000363
Frank, B., Enkawa, T., & Schvaneveldt, S. J. (2014). How do the success factors driving repurchase intent differ between male and female customers? Journal of the Academy of Marketing Science, 42(2), 171–185. https://doi.org/10.1007/s11747-013-0344-7
Guenzi, P., & Georges, L. (2010). Interpersonal trust in commercial relationships: Antecedents and consequences of customer trust in the salesperson. European Journal of Marketing, 44(1–2), 114–138. https://doi.org/10.1108/03090561011008637
Han, J., Kamber, M., & Pei, J. (2011). Data Mining. Concepts and Techniques, 3rd Edition (The Morgan Kaufmann Series in Data Management Systems).
Hosmer, D. W., Hosmer, T., Le Cessie, S., & Lemeshow, S. (1997). A COMPARISON OF GOODNESS-OF-FIT TESTS FOR THE LOGISTIC REGRESSION MODEL. In STATISTICS IN MEDICINE (Vol. 16). John Wiley & Sons.
Hu, H. Y. (2019). Research on customer churn prediction using logistic regression model. Advances in Intelligent Systems and Computing, 885, 344–350. https://doi.org/10.1007/978-3-030-02804-6_46
Jain, H., Khunteta, A., & Srivastava, S. (2020). Churn Prediction in Telecommunication using Logistic Regression and Logit Boost. Procedia Computer Science, 167, 101–112. https://doi.org/10.1016/j.procs.2020.03.187
Kamakura, W. A., Wedel, M., de Rosa, F., & Mazzon, J. A. (2003). Cross-selling through database marketing: A mixed data factor analyzer for data augmentation and prediction. International Journal of Research in Marketing, 20(1), 45–65. https://doi.org/10.1016/S0167-8116(02)00121-0
Karp, A. H. (n.d.). USING LOGISTIC REGRESSION TO PREDICT CUSTOMER RETENTION.
Kumar, A., & Janakiraman, M. (2010). Application of data mining techniques for customer lifetime value parameters: a review “Application of data mining techniques for customer lifetime value parameters: a review” Application of data mining techniques 515. In Int. J. Business Information Systems (Vol. 6, Issue 4).
Latifah, R., Setia Wulandari, E., & Priadhana Edi Kreshna, dan. (2019). Model Decision Tree untuk Prediksi Jadwal Kerja menggunakan Scikit-Learn (Vol. 16).
Lee, W.-M. (n.d.). Python machine learning.
Li, M., China Center for Industrial Security Research, Beijing jiao tong da xue. International Center for Informatics Research, Beijing jiao tong da xue. School of Economics and Management, IEEE Systems, M., & Institute of Electrical and Electronics Engineers. (n.d.). 5th International Conference on Industrial Economics System and Industrial Security Engineering : IEIS 2018 : proceeding : August 3-6, 2018, Toronto, Canada, with satellite sessions in Beijing, China.
Poufinas, T., & Michaelide, G. (2018). Determinants of Life Insurance Policy Surrenders. Modern Economy, 09(08), 1400–1422. https://doi.org/10.4236/me.2018.98089
Prinzie, A., & Van den Poel, D. (2008). Random Forests for multiclass classification: Random MultiNomial Logit. Expert Systems with Applications, 34(3), 1721–1732. https://doi.org/10.1016/j.eswa.2007.01.029
Sabbeh, S. F. (2018). Machine-Learning Techniques for Customer Retention: A Comparative Study. In IJACSA) International Journal of Advanced Computer Science and Applications (Vol. 9, Issue 2). www.ijacsa.thesai.org
Seguchi, M. (2022). Figuring Out Commercial Gimmicks Influencing Consumer Engagement from Psychological Change Points. Advances in Social Sciences Research Journal, 9(2), 190–210. https://doi.org/10.14738/assrj.92.11738
Staudt, Y., & Wagner, J. (2022). Factors Driving Duration to Cross-Selling in Non-Life Insurance: New Empirical Evidence from Switzerland. Risks, 10(10). https://doi.org/10.3390/risks10100187
Tsai, C. F., hu, Y. H., Hung, C. S., & Hsu, Y. F. (2013). A comparative study of hybrid machine learning techniques for customer lifetime value prediction. Kybernetes, 42(3), 357–370. https://doi.org/10.1108/03684921311323626
Verbeke, W., Dejaeger, K., Martens, D., Hur, J., & Baesens, B. (2012). New insights into churn prediction in the telecommunication sector: A profit driven data mining approach. European Journal of Operational Research, 218(1), 211–229. https://doi.org/10.1016/j.ejor.2011.09.031
Zhu, J., Lai, M., & Tsay, W. (2016). The Factors Influencing the Repurchasing Intention of Bank Insurance in Taiwan.