Value Per Transaction as an Incremental Predictor of Customer Profitability in Commercial Banking

In commercial banking, customers' contributions to profitability are essential to understanding the economic value of customer relationships. Traditional recency, frequency, and monetary (RFM) measures capture customer behavior, but the monetary measure captures only total transaction value, not individual transaction value. This study examines whether Value per Transaction (VPT) adds predictive power to RFM measures when assessing customer profitability. Using anonymized transaction data from 884,265 customers, the study applied descriptive analysis, Spearman correlation, logistic regression, and comparative predictive modeling to assess VPT’s validity. The results showed a moderate positive correlation between RFM score and VPT (ρ = 0.354, p < 0.001), suggesting a positive but not strong association. Logistic regression also showed that VPT remained statistically significant after Recency, Frequency, and Monetary value were added to the model (β = 1.936, p < 0.001). Predictive performance improved when VPT was combined with RFM: the AUC-ROC rose from 0.956 to 0.991 in the RFM–VPT model. These findings indicate that per-transaction value offers predictive information beyond traditional RFM metrics and highlight the importance of transaction-level value measures in analyzing customer profitability in commercial banking

Value per Transaction (VPT); Customer Profitability; RFM Analysis; Predictive Analytics; Customer Segmentation; Commercial Banking; Transactional Behaviour

1. Amendah, E. R., Kohli, A., Kumthekar, N., & Singh, G. (2023). Impact of financial and nonfinancial constructs on customer lifetime value (CLV): US retailers’ perspective. Journal of Relationship Marketing, 22(3), 202–237. [Google Scholar] [Crossref]

2. Ho, T., Cao, C. T., Tran, B. N., & Nguyen, L. T. M. (2025). Dynamic FPM: An integrated approach to customer segmentation and purchase behaviour prediction. Journal of Strategic Marketing, 1–24. [Google Scholar] [Crossref]

3. Kanchanapoom, K., & Chongwatpol, J. (2023). Integrated customer lifetime value (CLV) and customer migration model to improve customer segmentation. Journal of Marketing Analytics, 11(2), 172–185. [Google Scholar] [Crossref]

4. Kumar, A., Singh, K. U., Kumar, G., Choudhury, T., & Kotecha, K. (2023, October). Customer lifetime value prediction: Using machine learning to forecast CLV and enhance customer relationship management. In 2023 7th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) (pp. 1–7). IEEE. [Google Scholar] [Crossref]

5. Mohammed, S. A., Rashid, M. M., Obeid, I. K., Mohamed, M. J., & Kamil, H. H. (2026). Developing a hybrid predictive model for measuring customer lifetime value (CLV) based on marketing and accounting data and its role in improving management decisions: An applied study in Iraqi private banks. NIU Journal of Management Sciences, 12(2), 163–180. [Google Scholar] [Crossref]

6. Omran, M., Hamza, K., & Elghamrawy, S. (2024). Advancing customer segmentation in banking: Harnessing machine learning and H2O for personalized insights. In International Conference on Advanced Intelligent Systems and Informatics (pp. 246–256). Springer. [Google Scholar] [Crossref]

7. Patil, P. P. (2025). A data-driven approach to customer segmentation and customer lifetime value prediction in retail and e-commerce (Doctoral dissertation, National College of Ireland). [Google Scholar] [Crossref]

8. Rajesh, S. (2025, March). Optimizing customer profiling in the automobile parts sector: Integrating RFM analysis with advanced clustering techniques. In International Conference on Computing and Machine Learning (pp. 203–215). Springer Nature Singapore. [Google Scholar] [Crossref]

9. Rana, A. D., Hadisantoso, Q. C. M., & Girsang, A. S. (2024). RFM-T model clustering analysis in improving customer segmentation. [Google Scholar] [Crossref]

• Proposed Framework and Features of SeaCure: An IoT-Based GPS Monitoring and Emergency Alert System Using LoRa Technology for Small-Scale Fisherfolk