Predicting Customer Satisfaction of After-Sales Services Using Machine Learning in Customer Relationship Management (CRM)
Subject Areas : Management
Hooman Abaei
1
,
Sadegh Abedi
2
*
1 - Department of Industrial Management, Qazvin Branch, Islamic Azad University, Qazvin, Iran
2 - Department of Industrial Management, Qazvin Branch, Islamic Azad University, Qazvin, Iran
Keywords: Machine learning, fuzzy clustering, fuzzy decision tree, customer satisfaction, customer relationship management,
Abstract :
Background and Objective: Customer Relationship Management (CRM) is an effective tool for identifying and analyzing customer needs. Combining it with machine learning algorithms allows the development of customer satisfaction prediction models that can predict the probability of customer satisfaction with high accuracy. In addition to managerial decision-making at the operational level, these models are also used in formulating macro customer-oriented policies. The aim of this study is to identify the main factors affecting customer satisfaction and provide a model for predicting satisfaction levels in the automotive industry. Methodology: This is an applied study and data related to 1200 after-sales service customers of an automotive company was collected. After cleaning and normalizing the data, two machine learning algorithms including fuzzy clustering (FCM) and fuzzy decision tree (FDT) were used for analysis. Also, the validity of the models was measured with indicators such as accuracy, MAE, and RMSE. Findings: The results showed that customers fall into three main clusters including "satisfied", "dissatisfied" and "average". The variables of response time (30%) and service cost (25%) had the greatest impact on customer satisfaction. The accuracy of the fuzzy decision tree model was calculated to be 89% and its RMSE error was 0.12, which indicates the optimal performance of the model. Conclusion: This study showed that the use of machine learning algorithms, especially fuzzy clustering and fuzzy decision tree, can help managers identify different groups of customers, predict their satisfaction levels and develop targeted strategies. The results of this study can be used as a practical model for improving after-sales services in the automotive industry and other similar industries. The use of smart technologies and customer relationship management (CRM) systems for continuous data analysis is recommended.
1. Abdollahi, A., Shekouhiyar, S., & Ghadari, M. (1395). Measuring customer satisfaction with online trading services using Kano fuzzy approach and data mining. Financial Management Perspective, 6(4), 95–114. https://sid.ir/paper/503372/fa (in Persian)
2. Akhavan, F., & Hassannayebi, E. (2024). A hybrid machine learning with process analytics for predicting customer experience in online insurance services industry. Decision Analytics Journal, 11, 100452. https://doi.org/10.1016/j.dajour.2024.100452
3. Ashraf, A., Rayed, C. A., Awad, N. A., & Sabry, H. M. (2025). A framework for customer segmentation to improve marketing strategies using machine learning. Procedia Computer Science, 260, 616–625. https://doi.org/10.1016/j.procs.2025.03.240
4. Bassiouni, M. M., Chakrabortty, R. K., Sallam, K. M., & Hussain, O. K. (2024). Deep learning approaches to identify order status in a complex supply chain. Expert Systems with Applications, 250, 123947. https://doi.org/10.1016/j.eswa.2024.123947
5. Bose, I., & Chen, X. (2015). Detecting the migration of mobile service customers using fuzzy clustering. Information & Management, 52(2), 227–238. https://doi.org/10.1016/j.im.2014.11.001
6. Brunner, M., Tripathi, S., Gundolf, K., Bachmann, N., Thienemann, A. K., Tüzün, A., Pöchtrager, S., & Jodlbauer, H. (2025). Enhancing customer satisfaction through digitalization: Past, present and possible future approaches. Procedia Computer Science, 253, 2929–2940. https://doi.org/10.1016/j.procs.2025.02.017
7. Donyapour, H., & Abdavi, F. (1399). A conceptual model of factors affecting customer satisfaction in sports stores. Sports Marketing Studies, 1(2), 100–132. https://sid.ir/paper/381548/fa (in Persian)
8. Gholizadeh, H., & Sarbandi, S. (1399). Evaluation of the impact of total quality management application on customer satisfaction and loyalty. Business Studies, 18(103), 101–113. https://sid.ir/paper/391603/fa (in Persian)
9. Hashemi Golsafidi, A., Lashgari, Z., & Hajihah, Z. (1400). Application of machine learning to detect accounting distortions. Journal of Accounting and Auditing Management, 10(37), 271–283. https://sid.ir/paper/1045819/fa (in Persian)
10. Khedr, A. M., & Rani, S. S. (2024). Enhancing supply chain management with deep learning and machine learning techniques: A review. Journal of Open Innovation: Technology, Market, and Complexity, 10(4), 100379. https://doi.org/10.1016/j.joitmc.2024.100379
11. Kiumarth, M., & Niakan, L. (1400). Evaluation of customer satisfaction with life insurance policies. Insurance Research Journal, 36(1), 87–119. https://sid.ir/paper/986327/fa (in Persian)
12. Liu, J. (2023). Design and application of human resource management system based on data mining technology. Procedia Computer Science, 228, 241–252. https://doi.org/10.1016/j.procs.2023.11.028
13. Pawełek-Lubera, E., Przyborowski, M., Ślęzak, D., & Wasilewski, A. (2025). Multi-criteria selection of data clustering methods for e-commerce personalization. Applied Soft Computing, 182, 113559. https://doi.org/10.1016/j.asoc.2025.113559
14. Rawat, S., Rawat, A., Kumar, D., & Sabitha, A. S. (2021). Application of machine learning and data visualization techniques for decision support in the insurance sector. International Journal of Information Management Data Insights, 1(2), 100012. https://doi.org/10.1016/j.jjimei.2021.100012
15. Sadat Rasoul, S. M., Ebadi, O. M., & Bakhtiari, M. S. (1400). Identifying the impact of possible data manipulation on corporate customer credit scoring models using data mining. Industrial Management Perspective, 11(3), 45–67. https://sid.ir/paper/1045505/fa (in Persian)
16. Shahroodi, K., Darestani, S. A., Soltani, S., & Eisazadeh Saravani, A. (2024). Developing strategies to retain organizational insurers using a clustering technique: Evidence from the insurance industry. Technological Forecasting and Social Change, 201, 123217. https://doi.org/10.1016/j.techfore.2024.123217
17. Shadmehr, M., Heshmati, Z. A., Saqafi, F., & Vaisi, H. (1394). Modeling patient satisfaction with physicians based on machine learning methods. Information and Communication Technology Iran, 7(23–24), 1–23. https://sid.ir/paper/171492/fa (in Persian)
18. Sohrabi, B., Reyisi Vanani, I., & Keshavarzi, S. (1397). Developing a model to predict customer satisfaction with software support services using data mining. Strategic Management Researches, 24(68), 115–133. https://sid.ir/paper/513557/fa (in Persian)
19. Sun, X., Wang, Z., Zhou, M., Wang, T., & Li, H. (2024). Segmenting tourists’ motivations via online reviews: An exploration of the service strategies for enhancing tourist satisfaction. Heliyon, 10(1), e23539. https://doi.org/10.1016/j.heliyon.2023.e23539
20. Wang, J., Wu, J., Sun, S., & Wang, S. (2024). The relationship between attribute performance and customer satisfaction: An interpretable machine learning approach. Data Science and Management, 7(3), 164–180. https://doi.org/10.1016/j.dsm.2024.01.003