A MACHINE LEARNING SYSTEM ARCHITECTURE FOR PROACTIVE CUSTOMER CHURN PREDICTION

Ricky Pieter Palembangan; Ahmad Nurul  Fajar

doi:10.46764/teknimedia.v7i1.377

Ricky Pieter Palembangan Universitas Bina Nusantara
Ahmad Nurul Fajar Universitas Bina Nusantara

DOI: https://doi.org/10.46764/teknimedia.v7i1.377

Keywords: Banking Technology, Customer Churn, Machine Learning, Predictive Analytics, System Architecture

Abstract

The hyper-competitive credit card industry faces growing challenges from digital disruption and evolving consumer expectations, demanding a shift from reactive to proactive customer retention strategies. Traditional reactive approaches prove ineffective as customer decisions often reach irreversible stages before intervention. This study aims to develop and evaluate a comprehensive data-driven framework for predicting customer churn at PT XYZ, a leading Indonesian banking institution, and design a scalable system architecture with CRM integration and real-time analytics dashboard for operational deployment. Following the CRISP-DM framework, we comparatively evaluate Logistic Regression, Decision Tree, and Random Forest using a dataset of 11,314 customer records. Model performance evaluation encompasses multiple metrics including Accuracy, Precision, Recall, F1-Score, AUC. Random Forest algorithm demonstrated superior performance, achieving an AUC of 0.98 and accuracy of 97 percent. Feature importance analysis revealed customer transaction inactivity and credit utilization patterns as the most critical churn predictors, with transaction count contributing 41.59% importance score. The research successfully establishes a robust foundation for data-driven customer retention strategies, providing PT XYZ with a comprehensive blueprint for institutionalizing proactive retention strategies that can minimize revenue losses and secure competitive advantages in an increasingly dynamic market environment.

References

[1] X. Vives, “Digital Disruption in Banking,” vol. 29, p. 36, 2025, doi: 10.1146/annurev-financial-100719.
[2] P. Gomber et al., “On the Fintech revolution: Inter-preting the forces of innovation, disruption and transformation in financial services,” 2018. [Online]. Available: https://ink.library.smu.edu.sg/sis_research
[3] P. E. Pfeifer, “The optimal ratio of acquisition and retention costs,” Journal of Targeting, Measure-ment and Analysis for Marketing, vol. 13, no. 2, pp. 179–188, 2005, doi: 10.1057/palgrave.jt.5740142.
[4] B. Zhang, “Customer Churn in Subscription Busi-ness Model-Predictive Analytics on Customer Churn,” 2023.
[5] S. Gupta, A. Leszkiewicz, V. Kumar, T. Bijmolt, and D. Potapov, “Digital Analytics: Modeling for In-sights and New Methods,” Journal of Interactive Marketing, vol. 51, pp. 26–43, Aug. 2020, doi: 10.1016/J.INTMAR.2020.04.003.
[6] Neeraj Kripalani, “Predictive Analytics for Custom-er Retention: A Data-Driven Framework for Proac-tive Engagement and Satisfaction Management,” International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 10, no. 6, pp. 1109–1116, Nov. 2024, doi: 10.32628/cseit241061149.
[7] A. Agnihotri and R. Saravanakumar, “Customer Retention in Banking: Utilizing AI and Machine Learning for Predictive Churn Analysis,” in 2025 3rd International Conference on Intelligent Sys-tems, Advanced Computing and Communication (ISACC), 2025, pp. 140–144. doi: 10.1109/ISACC65211.2025.10969188.
[8] J. B. G. Brito et al., “A framework to improve churn prediction performance in retail banking,” Finan-cial Innovation, vol. 10, no. 1, Dec. 2024, doi: 10.1186/s40854-023-00558-3.
[9] L. Breiman, “Random Forests,” 2001.
[10] P. Chapman, “CRISP-DM 1.0: Step-by-step data mining guide,” p., 2000, [Online]. Available: https://consensus.app/papers/crispdm-10-stepbystep-data-mining-guide-chapman/1a6fabb85d3453d9be96ec2c18e14c77/
[11] A. Muneer, R. F. Ali, A. Alghamdi, S. M. Taib, A. Almaghthawi, and E. A. Abdullah Ghaleb, “Predict-ing customers churning in banking industry: A ma-chine learning approach,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 26, no. 1, pp. 539–549, Apr. 2022, doi: 10.11591/ijeecs.v26.i1.pp539-549.
[12] N. N. A. Nanda, Y. Farida, and W. D. Utami, “Im-plementation of SMOTE to Improve the Perfor-mance of Random Forest Classification in Credit Risk Assessment in Banking,” INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi, vol. 9, no. 2, pp. 158–177, Jul. 2025, doi: 10.29407/intensif.v9i2.23930.
[13] E. Dumitrescu, S. Hué, C. Hurlin, and S. Tokpavi, “Machine Learning or Econometrics for Credit Scor-ing: Let’s Get the Best of Both Worlds Machine Learning or Econometrics for Credit Scoring: Let’s Get the Best of Both Worlds *,” 2021. [Online]. Available: https://hal.science/hal-02507499v3
[14] J. Abasova, P. Tanuska, and S. Rydzi, “Big data—knowledge discovery in production industry data storages—implementation of best practices,” Ap-plied Sciences (Switzerland), vol. 11, no. 16, Aug. 2021, doi: 10.3390/app11167648.
[15] K. Peng, Y. Peng, and W. Li, “Research on customer churn prediction and model interpretability analy-sis,” PLoS One, vol. 18, no. 12 December, Dec. 2023, doi: 10.1371/journal.pone.0289724.
[16] D. AL-Najjar, N. Al-Rousan, and H. AL-Najjar, “Machine Learning to Develop Credit Card Cus-tomer Churn Prediction,” Journal of Theoretical and Applied Electronic Commerce Research, vol. 17, no. 4, pp. 1529–1542, Dec. 2022, doi: 10.3390/jtaer17040077.
[17] D. M. Melian, A. Dumitrache, S. Stancu, and A. Na-stu, “Customer Churn Prediction in Telecommuni-cation Industry. A Data Analysis Techniques Ap-proach,” Postmodern Openings, vol. 13, no. 1 Sup1, pp. 78–104, Mar. 2022, doi: 10.18662/po/13.1sup1/415.
[18] K. Gopalakrishnan, “Comparative Analysis of Ma-chine Learning Algorithms for Bank Customer Churn Prediction,” International Journal of Science and Research (IJSR), vol. 12, no. 6, pp. 2980–2983, Jun. 2023, doi: 10.21275/sr24531143837.
[19] A. Khattak, Z. Mehak, H. Ahmad, M. U. Asghar, M. Z. Asghar, and A. Khan, “Customer churn predic-tion using composite deep learning technique,” Sci. Rep., vol. 13, no. 1, Dec. 2023, doi: 10.1038/s41598-023-44396-w.
[20] M. Shahabikargar, A. Beheshti, X. Zhang, J. Foo, and A. Jolfaei, “A comprehensive survey on cus-tomer churn analysis studies,” Journal of Infor-mation and Telecommunication, 2025, doi: 10.1080/24751839.2025.2528440.
[21] M. Imani, M. Joudaki, A. Beikmohammadi, and H. Arabnia, “Customer Churn Prediction: A Systematic Review of Recent Advances, Trends, and Challeng-es in Machine Learning and Deep Learning,” Mach. Learn. Knowl. Extr., vol. 7, no. 3, p. 105, Sep. 2025, doi: 10.3390/make7030105.
[22] S. S. Poudel, S. Pokharel, and M. Timilsina, “Ex-plaining customer churn prediction in telecom indus-try using tabular machine learning models,” Ma-chine Learning with Applications, vol. 17, p. 100567, Sep. 2024, doi: 10.1016/j.mlwa.2024.100567.
[23] A. G. Văduva, S. V. Oprea, A. M. Niculae, A. Bâra, and A. I. Andreescu, “Improving Churn Detection in the Banking Sector: A Machine Learning Approach with Probability Calibration Techniques,” Electron-ics (Switzerland), vol. 13, no. 22, Nov. 2024, doi: 10.3390/electronics13224527.
[24] R. Bhuria et al., “Ensemble-based customer churn prediction in banking: a voting classifier approach for improved client retention using demographic and behavioral data,” Discover Sustainability, vol. 6, no. 1, Dec. 2025, doi: 10.1007/s43621-025-00807-8.
[25] D. Y. C. Wang, L. A. Jordanger, and J. C.-W. Lin, “Explainability of Highly Associated Fuzzy Churn Patterns in Binary Classification,” Oct. 2024, [Online]. Available: http://arxiv.org/abs/2410.15827
[26] B. Chen, “From Logistic Regression to Deep Learn-ing: Machine Learning Advances for Credit Card Churn,” 2024.
[27] H. Ghallab, M. Nasr, and H. Fahmy, “Enhancing Customer Churn Analysis by Using Real-Time Ma-chine Learning Model,” International Journal of Advanced Computer Science and Applications, vol. 16, no. 5, pp. 388–396, 2025, doi: 10.14569/IJACSA.2025.0160538.
[28] R. Krishna, D. Jayanthi, D. S. Shylu Sam, K. Ka-vitha, N. K. Maurya, and T. Benil, “Application of machine learning techniques for churn prediction in the telecom business,” Results in Engineering, vol. 24, Dec. 2024, doi: 10.1016/j.rineng.2024.103165.
[29] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Com-puting Machinery, Aug. 2016, pp. 785–794. doi: 10.1145/2939672.2939785.
[30] S. M. Lundberg, P. G. Allen, and S.-I. Lee, “A Uni-fied Approach to Interpreting Model Predictions.” [Online]. Available: https://github.com/slundberg/shap