Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM66946
Volume:
10 |
8 |
Aug 2026
Pages:
1-9
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Management Studies
Ballari Institute of Technology and Management
Computer Science and Engineering
Ballari Institute of Technology and Management
Retail banks accumulate large, heterogeneous customer bases, but existing literature and industry practice often treat customer value measurement, behavioural segmentation, and profitability estimation as separate exercises rather than a single connected pipeline. This study addresses that gap by building an integrated, data-driven framework that combines Recency-Frequency-Monetary (RFM) analysis, K-Means clustering, and a customer profitability/Customer Lifetime Value (CLV) model, applied to a publicly available, large-scale retail banking transaction dataset. Using 10,48,567 anonymised transaction records sourced from Kaggle, the data was cleaned to a verified 10,40,794 records covering 8,78,763 unique customers. RFM scoring classified customers into six behavioural segments, and K-Means clustering (K = 5) grouped them into five value-based segments, which were then compared with the independent RFM classification. A profitability model combining a transaction-fee revenue proxy, a deposit-based Net Interest Margin (NIM) proxy, and a servicing-cost estimate produced a total estimated gross profit of Rs 345.88 Crore and a projected 36-month CLV of Rs 2,175.02 Crore, with 84.9 per cent of customers profitable. The analysis found that deposit-based revenue accounts for 99.8 per cent of total revenue, that profit is heavily concentrated (7.27 per cent of customers generate 70.49 per cent of profit), and that age distributions were broadly similar across behavioural clusters — a finding with direct implications for how retention and cross-selling should be targeted. The study translates these findings into segment-specific retention and cross-selling recommendations and discusses their implications for customer relationship management in retail banking, while documenting the assumptions and limitations of the modelling approach used.
KEYWORDS
This study set out to build a structured, customer-level view of profitability for a retail banking customer base, bringing RFM analysis, K-Means clustering, and an explicit profitability/CLV model together into a single applied pipeline rather than treating them separately, as much of the existing literature does. Working through a large, publicly available transactional dataset, the analysis shows that behavioural segmentation and profitability measurement genuinely need each other: segments that look similar in size or engagement can differ sharply in the value they actually hold, and dimensions such as customer age can matter for profitability without being visible in the segmentation at all. The retention and cross-selling recommendations that follow from this analysis are offered as a replicable framework for retail banking customer management — one built and documented with its assumptions and limitations made explicit, rather than as a substitute for a bank's own internal financial and customer data.
1. Bansal, S. (n.d.). Bank Customer Segmentation [Dataset]. Kaggle. Retrieved from https://www.kaggle.com/datasets/shivamb/bank-customer-segmentation 2. Fader, P. S., Hardie, B. G. S., & Lee, K. L. (2005). RFM and CLV: Using iso-value curves for customer base analysis. Journal of Marketing Research, 42(4), 415–430. 3. Haenlein, M., Kaplan, A. M., & Beeser, A. J. (2007). A model to determine customer lifetime value in a retail banking context. European Management Journal, 25(3), 221–234. 4. Hughes, A. M. (1994). Strategic database marketing. Chicago: Probus Publishing Company. 5. McKinney, W. (2010). Data structures for statistical computing in Python. Proceedings of the 9th Python in Science Conference. 6. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830. 7. Reinartz, W. J., & Kumar, V. (2000). On the profitability of long-life customers in a noncontractual setting: An empirical investigation and implications for marketing. Journal of Marketing, 64(4), 17–35. 8. Wei, J. T., Lin, S. Y., & Wu, H. H. (2010). A review of the application of RFM model. African Journal of Business Management, 4(19), 4199–4206.
Publication Date
8/26/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
4
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...