A Machine Learning–Based Approach to Improving Customer Experience and Service Personalization: Customer Segmentation and Decision Rule Extraction

Mehrnaz  Maleki; Mohammadreza  Sanaei; Seyed Yashar  Banihashem; Safanaz  Heydari

Authors

Mehrnaz Maleki Department of IT Management, Qa.C., Islamic Azad University, Qazvin, Iran Author https://orcid.org/0009-0008-0662-1031
Mohammadreza Sanaei Department of IT Management, Qa.C., Islamic Azad University, Qazvin, Iran Corresponding author https://orcid.org/0009-0007-1653-0718
Seyed Yashar Banihashem Assistant Professor, Department of Electrical and Computer Engineering, Buein Zahra Technical University, Buein Zahra, Iran Author https://orcid.org/0000-0002-2456-7920
Safanaz Heydari Department of Management, Miy.C., Islamic Azad University, Miyandoab, Iran Author https://orcid.org/0000-0002-5312-9129

Keywords:

Machine Learning, Customer Segmentation, Customer Experience, Service Personalization, K-Means Clustering, Decision Tree, Predictive Analytics, Customer Relationship Management

Abstract

This study aimed to develop a machine learning-based framework for improving customer experience and service personalization through multidimensional customer segmentation and extraction of interpretable decision rules. This applied, quantitative, cross-sectional study was conducted among 1,248 customers in Tehran, Iran. Demographic, transactional, behavioral, and customer-experience data were integrated into a unified analytical dataset. Customer behavior was assessed using recency, frequency, monetary value, service-use breadth, digital interaction, promotional responsiveness, complaint behavior, and customer-service contact indicators, while customer experience, perceived personalization, satisfaction, loyalty intention, and recommendation intention were measured using structured Likert-scale items. After preprocessing, standardization, and data-quality assessment, K-means clustering was applied to identify homogeneous customer segments. Candidate cluster solutions were evaluated using the silhouette coefficient, Calinski-Harabasz index, Davies-Bouldin index, and within-cluster sum of squares. Decision Tree, Random Forest, and Gradient Boosting algorithms were subsequently used to predict cluster membership, and interpretable rules were extracted from the optimized Decision Tree. The four-cluster solution demonstrated the strongest internal validity, with a silhouette coefficient of 0.561, Calinski-Harabasz index of 668.45, and Davies-Bouldin index of 0.714. Significant differences were observed among the four clusters across all principal transactional, behavioral, and customer-experience variables (all p < 0.001). Random Forest achieved the highest predictive accuracy (0.928), followed by Gradient Boosting (0.919) and Decision Tree (0.887). Macro F1-scores were 0.925, 0.915, and 0.882, respectively. Purchase recency, monetary value, purchase frequency, customer experience, perceived personalization, digital interaction, promotional responsiveness, and complaint behavior emerged as the most influential predictors of segment membership. Integrating unsupervised clustering with supervised machine learning and interpretable decision-rule extraction provides an effective framework for identifying heterogeneous customer groups and supporting targeted, data-driven personalization strategies.

References

[1] A. Ashraf, C. A. Rayed, N. A. Awad, and H. M. Sabry, "A Framework for Customer Segmentation to Improve Marketing Strategies Using Machine Learning," Procedia Computer Science, vol. 260, pp. 616-625, 2025, doi: 10.1016/j.procs.2025.03.240.

[2] S. N. Lathifah and Z. F. Azzahra, "AI-Driven Customers Segmentation Using K-Means Clustering," G-Tech: Jurnal Teknologi Terapan, vol. 9, no. 1, pp. 320-329, 2025, doi: 10.70609/gtech.v9i1.6202.

[3] J. George and R. Sona, "Leveraging Machine Learning for Customer Segmentation in Retail," Interantional Journal of Scientific Research in Engineering and Management, vol. 08, no. 03, pp. 1-9, 2024, doi: 10.55041/ijsrem29102.

[4] D. Rajan and V. H. Josephine, "Data Mining Techniques to Enhance Customer Segmentation and Targeted Marketing Strategies," in 2024 15th International Conference on Computing Communication and Networking Technologies, 2024, pp. 1-5, doi: 10.1109/ICCCNT61001.2024.10725770.

[5] X. Yan, Y. Li, F. Nie, and R. Li, "Bank Customer Segmentation and Marketing Strategies Based on Improved DBSCAN Algorithm," Applied Sciences, vol. 15, no. 6, 2025.

[6] M. T. Taghvaifard, A. Mohammadi Khani, and F. Lotfi, "Customer segmentation in electronic banking using electronic transactions and demographic information (Case study: Refah Bank)," Approaches in Business Management, vol. 7, pp. 48-61, 2021.

[7] I. Lewaaelhamd, "Customer segmentation using machine learning model: An application of RFM analysis," Journal of Data Science and Intelligent Systems, vol. 2, no. 1, pp. 29-36, 2024, doi: 10.47852/bonviewJDSIS32021293.

[8] M. A. Rahim, M. Mushafiq, S. Khan, and Z. A. Arain, "RFM-Based Repurchase Behavior for Customer Classification and Segmentation," Journal of Retailing and Consumer Services, vol. 61, p. 102566, 2021, doi: 10.1016/j.jretconser.2021.102566.

[9] P. Li, C. Wang, J. Wu, and R. Madleňák, "An E-commerce customer segmentation method based on RFM weighted K-means," in 2022 International Conference on Management Engineering, Software Engineering and Service Sciences, 2022, pp. 61-68, doi: 10.1109/ICMSS55574.2022.00017.

[10] A. B. Hadid, S. Bouguelia, and H. Kheddouci, "A New Method of B2B Customer Segmentation Based on Firmographic Data, and RFM and Graph Models," in 2024 IEEE International Conference on e-Business Engineering, 2024, pp. 81-86, doi: 10.1109/ICEBE62490.2024.00021.

[11] P. N. Nair, "Examining the Use of Ai-Powered Social Media Analytics for Target Customer Segmentation: A Systematic Review in Retail Industry," Eatp, pp. 1798-1805, 2024, doi: 10.53555/kuey.v30i4.1753.

[12] N. Sakina, A. P. Arun, and P. K. Gupta, "Optimizing Customer Segmentation: A Comparative Analysis of Clustering Algorithms Using Evaluation Metrics," in 2024 8th International Conference on Computational System and Information Technology for Sustainable Solutions, 2024, pp. 1-6, doi: 10.1109/CSITSS64042.2024.10816952.

[13] D. Bhargava, A. Bhargava, R. P. Melgarejo-Bolivar, A. M. Montes de Oca-Nina, and S. Chaudhury, "Enhancing Personalization of Customer Services in E-Commerce System Using Predictive Analytics," Fluctuation and Noise Letters, vol. 23, no. 02, p. 2440011, 2024, doi: 10.1142/S021947752440011X.

[14] M. S. Bhuiyan, "The Role of AI-Enhanced Personalization in Customer Experiences," Journal of Computer Science and Technology Studies, vol. 6, no. 1, pp. 162-169, 2024, doi: 10.32996/jcsts.2024.6.1.17.

[15] H. Katikar, "Enhancing Personalized Marketing Strategies and Customer Experiences Through AI-Driven Personalization," 2024, doi: 10.14293/pr2199.000976.v1.

[16] A. Arora, R. Kapale, P. Sharma, M. Nalavade, M. Saifee, and M. Ukey, "The Impact of AI-Driven Personalization on Customer Loyalty: A Meta-Analysis of E-commerce Studies," 2024: IEEE, pp. 1-6.

[17] S. H. Kim, S. Lee, D. Biswas, M. D. Shahnawaj, N. M. Kyoom, and P. K. Bhardwaj, "Personalization and Recommendation Systems: Leveraging Machine Learning Algorithms to Offer Personalized Product Recommendations and Content to Customers Based on Their Behavior, Preferences and Purchasing History," International Journal of Grid Computing & Applications, vol. 16, no. 2, pp. 1-4, 2025, doi: 10.5121/ijgca.2025.16201.

[18] S. Yang, Q. Li, D. Jang, and J. Kim, "Deep learning mechanism and big data in hospitality and tourism: Developing personalized restaurant recommendation model to customer decision-making," International Journal of Hospitality Management, vol. 121, p. 103803, 2024, doi: 10.1016/j.ijhm.2024.103803.

[19] M. Ashrafuzzaman, R. Parveen, M. A. Sumiya, and A. Rahman, "AI-Powered Personalization in Digital Banking: A Review of Customer Behavior Analytics and Engagement," (in English), American Journal of Interdisciplinary Studies, vol. 6, no. 1, pp. 40-71, 2025, doi: 10.63125/z9s39s47.

[20] P. S. P. Kumar and C. Ramu, "Two-Dimensional Customer Segmentation for Digital Custom Coupon Issuance Approach," International Journal of Multidisciplinary Research in Science Engineering and Technology, vol. 7, no. 05, pp. 10042-10052, 2024, doi: 10.15680/ijmrset.2024.0705076.

[21] S. Wu, W. C. Yau, T. S. Ong, and S. C. Chong, "Integrated Churn Prediction and Customer Segmentation Framework for Telco Business," IEEE Access, vol. 9, pp. 62118-62136, 2021, doi: 10.1109/ACCESS.2021.3073776.

[22] I. Huda, A. A. Suhendra, and M. A. Bijaksana, "Design of prediction model using data mining for segmentation and classification customer churn in e-commerce mall in mall," JOIV: International Journal on Informatics Visualization, vol. 7, no. 4, pp. 2280-2289, 2023, doi: 10.62527/joiv.7.4.2414.