Sharif Journal of Industrial Engineering & Management

Sharif Journal of Industrial Engineering & Management

Analysis of Customers' Lifetime Value with a Clustering Approach Based on Som Artificial Neural Networks and Markov Chain (Case Study: Pasargad Digital Bank)

Document Type : Article

Authors
Maral Mirzaei Moradi 1
Seyed Hoss Razavi H 2
Hannan Amoozad Mahdiraji 3
Ali Alikhani 4
1 Faculty of Industrial Management, University of Tehran, Kish International Campus, Iran
2 Department of Management, Faculty of Management and Financial Sciences, Khatam University, Tehran, Iran
3 Department of Technology and Innovation Management, Faculty of Industrial and Technology Management, University of Tehran, Tehran, Iran
4 Department of Industrial Management, Faculty of Management and Social Sciences, Islamic Azad University, North Tehran Branch, Tehran, Iran
10.24200/j65.2024.63417.2379
Abstract
Clustering of customers and analysis of their lifetime value is one of the basic strategies of policy making in production and marketing. Since the advertising strategies of many businesses are implemented regardless of the financial behavior clusters of customers and the expected income resulting from the dynamic financial behavior of customers, the advertising policy based on the customers’ lifetime value in the dynamic clusters of their financial behavior can save a lot of advertising and marketing costs to manage the costs imposed on businesses. This is despite the fact that the studies conducted in the field of customer lifetime value analysis have not paid attention to advertising strategies based on lifetime value. The existing methods for determining the lifetime value of customers rely on static clustering of customers' status, while customer clustering based on their financial behavior is a dynamic and time-varying phenomenon. Therefore, in this research, the lifetime value analysis of customers and the optimization of advertising strategy in the dynamic clusters of their financial behavior using a self-organizing neural network and dynamic stochastic programming have been discussed. For this purpose, based on the status of each customer belonging to a cluster during consecutive weeks, a Markov chain is formed from the clusters containing customers, and the lifetime value of customers is based on the transition probability matrices of customers' status from one cluster to another, and it is also estimated based on the expected income of customers in each cluster. The results showed that customer clustering with the self-organizing neural network method can explain at least 91% of the changes in the data. Also, the findings showed that the optimal advertising strategy for each cluster of customers with a certain expected income level will lead to different lifetime value for customers, which shows the importance of dynamic clustering of customers and determining the optimal level of advertising cost in each cluster to gain more customer lifetime value.
Keywords
Customer lifetime value
clustering
markov chain
SOM neural network
Subjects
1. Kumar, V. and Rajan, B., 2020. Customer Lifetime Value: What, How, And Why, The Routledge Companion to Strategic Marketing, pp.422–448. http://doi.org/10.4324/9781351038669
2. Libai, B., Bart, Y., Gensler, S., Hoffman, D.L., Indurkhya, N., van Bruggen, G.H. and Steven, A., 2020. Brave new world? on AI and the management of customer relationships. Journal of Interactive Marketing, 51(1), pp.44–56. http://doi.org/10.1016/j.intmar.2020.04.002
3. Pramono, P.P., Surjandari, I. and Laoh, E., 2019. Estimating customer segmentation based on customer lifetime value using two-stage clustering method. In 2019 16th International Conference on Service Systems and Service Management (ICSSSM), pp. 1–5. http://doi.org/10.1109/ICSSSM.2019.8887704
4. Kanchanapoom, K. and Chongwatpol, J., 2023. Integrated customer lifetime value (CLV) and customer migration model to improve customer segmentation. Journal of Marketing Analytics, 11(2), pp.172–185. http://doi.org/10.1057/s41270-022-00158-7
5. Marmol, M., Chamorro, A., Sandoval, M. and Liébana-Cabanillas, F., 2021. Maximizing customers' lifetime value using limited marketing resources. Marketing Intelligence & Planning, 39(8), pp.1058–1072. http://doi.org/10.1108/MIP-02-2021-0050
6. Manosuthi, N., Lee, J.S. and Han, H., 2021. Causal-predictive model of customer lifetime/influence value. Journal of Travel & Tourism Marketing, 38(5), pp.461–477. http://doi.org/10.1080/10548408.2021.1940422
7.Tekin, A.T., Kaya, T. and Cebi, F., 2022. Customer lifetime value prediction for gaming industry. Journal of Intelligent & Fuzzy Systems, 42(1), pp.87–96. http://doi.org/10.3233/JIFS-219177
8. Pradhan, S., Patel, G. and Priya, P., 2021. Measuring customer lifetime value. International Journal of the Analytic Hierarchy Process, 13(3), pp.1–16. http://doi.org/10.13033/ijahp.v13i3.892
9. Asadi, N. and Kazerooni, M., 2023. A stacked ensemble learning method for customer lifetime value prediction. Kybernetes, 53(7), pp.2342-2360. http://doi.org/10.1108/K-12-2022-1676
10. Reddy, K.B., Rani, G., Bhargavi, P. and Padmavathi, M., 2022. Prediction of customer lifetime value using machine learning. In Proceedings of Second Doctoral Symposium on Computational Intelligence: DoSCI, pp. 271–278.      http://doi.org/10.1007/978-981-16-3346-1_22
11. Badri, H. and Tran, A., 2022. Beyond customer lifetime valuation. In Proceedings of the ACM Web Conference, pp. 132–140. http://doi.org/10.1145/3485447.3512058
12. Katsikeas, C., Leonidou, L. and Zeriti, A., 2020. Revisiting international marketing strategy in a digital era. International Marketing Review, 37(3), pp.405–424. http://doi.org/10.1108/IMR-02-2019-0080
13. Fader, P.S., 2012. Customer Centricity: Focus on the Right Customers for Strategic Advantage, Wharton Digital Press. http://doi.org/10.2307/j.ctv2hdrfj0
14. Persson, A. and Ryals, L., 2010. Customer assets and customer equity. Marketing Theory, 10(4), pp.417–436. http://doi.org/10.1177/1470593110382828
15. Ryals, L. and Knox, S., 2007. Measuring and managing customer relationship risk in business markets. Industrial Marketing Management, 36(6), pp.823–833. http://doi.org/10.1016/j.indmarman.2006.06.017
16. Al-Dmour, R., Al-Dmour, H., Masa’deh, R. and Al-Hawasheen, M., 2020. The effect of customer lifestyle patterns on mobile banking use in Jordan. International Journal of Electronic Marketing and Retailing, 11(3), pp.239–258. http://doi.org/10.1504/IJEMR.2020.108121
17. Myburg, M. and Berman, S., 2022. Customer lifetime value prediction with k-means clustering and xgboost. In 2022 IEEE/ACM International Conference on ASONAM, pp. 298–302. http://doi.org/10.1109/ASONAM55673.2022.10068602
18. Ali, R., Pye, A., Mortier, R. and Crowcroft, J., 2021. Estimating customer lifetime value in the gaming industry using incomplete data. Mathematics in Industry Reports (MIIR), pp.1–36. http://doi.org/10.33774/miir-2021-rd4pd
19. von Focht, T., 2022. Customer Lifetime Value–Neue Anwendungsmöglichkeiten, In Marketing Analytics, pp.229–241. http://doi.org/10.1007/978-3-658-33809-1_13
20. Libai, B., Bart, Y., Gensler, S., Hoffman, D.L., Indurkhya, N., van Bruggen, G.H. and Steven, A., 2020. Brave new world? on AI and customer relationships. Journal of Interactive Marketing, 51(1), pp.44–56. http://doi.org/10.1016/j.intmar.2020.04.002
21. Shekary, M., 2021. Calculating CLV using Markov chain approach. Management Research in Iran, 22(4), pp.1–21. [In Persian]. https://mri.modares.ac.ir/m/article_474.html?lang=en
22. Waarden, L.M., 2007. The effects of loyalty programs on CLV. Journal of Retailing, 83(2), pp.223–236. http://doi.org/10.1016/j.jretai.2007.01.002
23. Donkers, B., Verhoef, P.C. and De Jong, M.G., 2007. Modeling CLV. Quantitative Marketing and Economics, 5, pp.163–190. http://doi.org/10.1007/s11129-006-9016-y
24. Batislam, E.M., Denizel, M. and Filiztekin, A., 2007. Validation of models for customer base analysis. International Journal of Research in Marketing, 24(3), pp.201–209. http://doi.org/10.1016/j.ijresmar.2006.12.005
25. Dandis, A.O., Al-Shboul, R., Al-Kasasbeh, M. and Al-Shammari, M., 2023. CLV in fast-food restaurants. The TQM Journal. 35(8), pp.2526-2546. http://doi.org/10.1108/TQM-08-2022-0248
26. Gadgil, K., Gill, S.S. and Abdelmoniem, A.M., 2023. Stacked regression approach for CLV. Journal of Economy and Technology. ahead-of-print. http://doi.org/10.48550/arXiv.2308.08502
27. Abidar, L., El Himer, S., El Bouchti, A. and Hachimi, H.E., 2023. Predicting customer segment changes. International Journal of Advanced Computer Science and Applications, 14(7), pp.910–920.  http://doi.org/10.14569/IJACSA.2023.0140799
28. Dandis, A.O. and Al Haj Eid, M.B., 2022. CLV and brand loyalty. The TQM Journal, 34(3), pp.476–493. http://doi.org/10.1108/TQM-12-2020-0311
29. Bakhshizadeh, E., Nasrabadi, H.A., Karamoozian, A. and Mahdavi, I., 2022. Customer clustering in software industry. International Journal of Industrial Engineering & Production Research, 33(1), pp.18–33. [In Persian]. http://doi.org/10.22068/ijiepr.33.1.1
30. De Marco, M., Mangano, G., Casale, G. and Raguseo, E., 2021. Cognitive analytics of clv using ann. Journal of Enterprise Information Management, 34(2), pp.679–696. http://doi.org/10.1108/JEIM-01-2020-0029
31. Bauer, J. and Jannach, D., 2021. Improved clv prediction with sequence-to-sequence learning. ACM Transactions on Knowledge Discovery from Data, 15(5), pp.1–37. http://doi.org/10.1145/3441444
32. Carneiro, F. and Miguéis, V., 2021. Estimating clv in the food industry. In Proceedings of the International Conference on Industrial Engineering and Operation Management, p.125. http://doi.org/10.46254/sa02.20210125
33. Hoseini Ravesh, S.M.H. and Moghaddam, A., 2023. CLV based on service quality in gyms. Sport Management Studies, 2(2), pp.19–36. [In Persian]. https://www.magiran.com/paper/2614412
34. Rajabiasli, M., Fatemi, M. and Khodadadi, A., 2023. Leading indicators of clv in sports clubs. Knowledge Management in Sport Journal, 2(4), pp.1–16. [In Persian]. http://doi.org/10.30495/kmsj.2022.1975357.1062
35. Rajabiasli, M., Fatemi, M. and Khodadadi, A., 2023. CLV prediction using GMDH neural networks. Sport Management Studies, 15(81) , pp.265-284. [In Persian]. http://doi.org/10.22089/smrj.2023.13662.3763
36. Safabakhsh, M. and Asayesh, F., 2023. Segmentation of bank customers based on CLV. Quarterly Studies in Banking Management and Islamic Banking, 8(19), pp.53–80. [In Persian]. http://doi.org/10.22034/jifb.2023.166991
37. Ghadirmohseni, M., Ayough, A. and Razavi Haji Agha, S.H., 2023. Profit function of bank customers using CLV. Quarterly Studies in Banking Management and Islamic Banking, 8(19), pp.23–52. [In Persian]. https://www.magiran.com/paper/2549150
38. Nabizade, F. and Rouhani, S., 2020. Clustering and prediction model of CLV. Journal of Industrial Management Perspective, 10(4), pp.41–63. [In Persian]. http://doi.org/10.52547/jimp.10.4.41
39. Esfidani, M.R. and Toopa Esfandiari, F., 2019. Factors affecting CLV in melli bank. Journal of Business Administration Researches, 11(21), pp.69–89. [In Persian]. http://doi.org/10.22034/JBAR.2019.1550
 
Sharif Journal of Industrial Engineering & Management
Volume 41, Issue 1 - Serial Number 1
September 2025
Pages 57-72