Proposing a New Framework Based on the RFM Model and Multivariate Time Series for Customer Segmentation and Behavior Analysis: A Case Study of a Food Industry Company

Document Type : Original Article

Authors

1 Department of Computer and Information Technology, Faculty of Engineering, University of Qom, Qom, Iran

2 Faculty of Information Technology and Computer Engineering, Azarbaijan Shahid Madani University, Tabriz, Iran

Abstract

Purpose: The objective of this study is to analyze customer behavior using multivariate time‑series data. After conducting a comprehensive analysis of customer behavior, customers are prioritized using the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) multi‑criteria decision‑making method. The results of this study can assist organizations in developing more effective and targeted marketing strategies.
Method: In this research, customers’ dynamic behavior is analyzed using the RFM (recency, frequency, monetary value) model represented as multivariate time‑series data. This approach is considered one of the most recent and practical methods for analyzing customer behavior over time. First, an ensemble time‑series clustering method is applied to identify customer clusters and analyze their behavioral patterns from different perspectives. Subsequently, key features are extracted from each time series and used as inputs to a classification model. Finally, the classifier model is interpreted using Shapley Additive Explanations (SHAP), which enables the calculation of the importance of each key feature. These key features and their corresponding weights are then used as inputs for the TOPSIS multi‑criteria decision‑making method to prioritize customers.
Findings: The findings indicate that representing customer purchase data as multivariate time‑series data based on RFM variables enables the identification of groups of customers with similar behavioral patterns over time. The proposed approach simultaneously considers RFM variables across time and provides a dynamic analysis of customer behavior. In addition, the application of the SHAP method allows for the interpretation of the classification model and the determination of the importance of critical behavioral features. Based on these weighted features, the TOPSIS method is applied to rank customers according to their importance and priority within marketing strategies. These results can support organizations in designing targeted and effective marketing initiatives.
Conclusion: The results demonstrate that the proposed approach enables the identification of customer behavioral patterns and facilitates more accurate customer prioritization. These analyses help organizations better understand customer dynamics and focus their marketing strategies on high‑value customers. Overall, the findings support organizations in improving marketing effectiveness and efficiency through a deeper understanding and analysis of customer behavior patterns

Keywords

Main Subjects

References

Abbasimehr, H., & Baghery, F. S. (2022). A novel time series clustering method with fine-tuned support vector regression for customer behavior analysis. Expert Systems with Applications, 204, 117584.
Abbasimehr, H., & Bahrini, A. (2022). An analytical framework based on the recency, frequency, and monetary model and time series clustering techniques for dynamic segmentation. Expert Systems with Applications, 192, 116373. doi:https://doi.org/10.1016/j.eswa.2021.116373.
Abbasimehr, H., & Shabani, M. (2019). Forecasting of customer behavior using time series analysis. Paper presented at the The 7th International Conference on Contemporary Issues in Data Science.
Abbasimehr, H., & Shabani, M. (2021a). A new framework for predicting customer behavior in terms of RFM by considering the temporal aspect based on time series techniques. Journal of Ambient Intelligence and Humanized Computing, 12(1), 515-531. doi:10.1007/s12652-020-02015-w
Abbasimehr, H., & Shabani, M. (2021b). A new methodology for customer behavior analysis using time series clustering: A case study on a bank’s customers. Kybernetes, 50(2), 221-242.
Aghabozorgi, S., Shirkhorshidi, A. S., & Wah, T. Y. (2015). Time-series clustering–a decade review. Information systems, 53, 16-38.
Akhondzadeh-Noughabi, E., & Albadvi, A. (2015). Mining the dominant patterns of customer shifts between segments by using top-k and distinguishing sequential rules. Management Decision, 53(9), 1976-2003.
Al-Naymat, G., Chawla, S., & Taheri, J. (2012). Sparsedtw: A novel approach to speed up dynamic time warping. arXiv preprint arXiv:1201.2969.
Alqurashi, T., & Wang, W. (2019). Clustering ensemble method. International Journal of Machine Learning and Cybernetics, 10, 1227-1246.
Alsayat, A. (2023). Customer decision-making analysis based on big social data using machine learning: a case study of hotels in Mecca. Neural Computing and Applications, 35(6), 4701-4722.
Barough, S. S., Safavi-Naini, S. A. A., Siavoshi, F., Tamimi, A., Ilkhani, S., Akbari, S., . . . Pourhoseingholi, M. A. (2023). Generalizable machine learning approach for COVID-19 mortality risk prediction using on-admission clinical and laboratory features. Scientific Reports, 13(1), 2399.
Batista, G. E., Keogh, E. J., Tataw, O. M., & De Souza, V. M. (2014). CID: an efficient complexity-invariant distance for time series. Data Mining and Knowledge Discovery, 28, 634-669.
Boongoen, T., & Iam-On, N. (2018). Cluster ensembles: A survey of approaches with recent extensions and applications. Computer Science Review, 28, 1-25.
Chouakria, A. D., & Nagabhushan, P. N. (2007). Adaptive dissimilarity index for measuring time series proximity. Advances in Data Analysis and Classification, 1, 5-21.
Coussement, K., Van den Bossche, F. A., & De Bock, K. W. (2014). Data accuracy's impact on segmentation performance: Benchmarking RFM analysis, logistic regression, and decision trees. Journal of Business Research, 67(1), 2751-2758.
Dhanushkodi, K., Bala, A., Kodipyaka, N., & Shreyas, V. (2024). Customer Behaviour Analysis and Predictive Modelling in Supermarket Retail: A Comprehensive Data Mining Approach. IEEE Access.
Doğan, O., Ayçin, E., & Bulut, Z. (2018). Customer segmentation by using RFM model and clustering methods: a case study in retail industry. International Journal of Contemporary Economics and Administrative Sciences, 8.
Duda, R., Hart, P., Stork, D., & Ionescu, A. (2000). Pattern classification, chapter nonparametric techniques. Wiley-Interscience Publication.
Ebadi Jalal, M., & Elmaghraby, A. (2024). Analyzing the Dynamics of Customer Behavior: A New Perspective on Personalized Marketing through Counterfactual Analysis. Journal of Theoretical and Applied Electronic Commerce Research, 19(3), 1660-1681.
Guerola-Navarro, V., Oltra-Badenes, R., Gil-Gomez, H., & Gil-Gomez, J.-A. (2020). Customer relationship management (CRM): a bibliometric analysis. International Journal of Services Operations and Informatics, 10(3), 242-268.
Heldt, R., Silveira, C. S., & Luce, F. B. (2021). Predicting customer value per product: From RFM to RFM/P. Journal of Business Research, 127, 444-453.
Hu, J., Du, Y., Mo, H., Wei, D., & Deng, Y. (2016). A modified weighted TOPSIS to identify influential nodes in complex networks. Physica A: Statistical Mechanics and its Applications, 444, 73-85.
Hu, Y.-H., Huang, T. C.-K., & Kao, Y.-H. (2013). Knowledge discovery of weighted RFM sequential patterns from customer sequence databases. Journal of Systems and Software, 86(3), 779-788. doi:https://doi.org/10.1016/j.jss.2012.11.016
Hughes, A. M. (2005). Strategic database marketing.McGraw-Hill Pub. Co.
Hwang, C.-L., Yoon, K., Hwang, C.-L., & Yoon, K. (1981). Methods for multiple attribute decision making. Multiple attribute decision making: methods and applications a state-of-the-art survey, 58-191.
Hyndman, R. J., Wang, E., & Laptev, N. (2015). Large-scale unusual time series detection. Paper presented at the 2015 IEEE international conference on data mining workshop (ICDMW).
Iam-On, N., Boongoen, T., & Garrett, S. (2010). LCE: a link-based cluster ensemble method for improved gene expression data analysis. Bioinformatics, 26(12), 1513-1519.
KATRAGADDA, V. (2022). Dynamic Customer Segmentation: Using Machine Learning to Identify and Address Diverse Customer Needs in Real-Time. IRE Journals, 5(10), 278-279.
Khajvand, M., & Tarokh, M. J. (2011). Estimating customer future value of different customer segments based on adapted RFM model in retail banking context. Procedia Computer Science, 3, 1327-1332.
Kim, E.-Y., Hwang, D.-U., & Ko, T.-W. (2012). Multiscale ensemble clustering for finding modules in complex networks. Physical Review E—Statistical, Nonlinear, and Soft Matter Physics, 85(2), 026119.
Liu, Y., & Chen, C. (2022). Improved RFM model for customer segmentation using hybrid meta-heuristic algorithm in medical IoT applications. International Journal on Artificial Intelligence Tools, 31(01), 2250009.
Lundberg, S. (2017). A unified approach to interpreting model predictions. arXiv preprint arXiv:1705.07874.
Montero, P., & Vilar, J. A. (2015). TSclust: An R package for time series clustering. Journal of Statistical Software, 62, 1-43.
Mosaddegh, A., Albadvi, A., Sepehri, M. M., & Teimourpour, B. (2021). Dynamics of customer segments: A predictor of customer lifetime value. Expert Systems with Applications, 172, 114606. doi:https://doi.org/10.1016/j.eswa.2021.114606
Pakzad, S. S., Roshan, N., & Ghalehnovi, M. (2023). Comparison of various machine learning algorithms used for compressive strength prediction of steel fiber-reinforced concrete. Scientific Reports, 13(1), 3646.
Paparrizos, J., & Gravano, L. (2017). Fast and accurate time-series clustering. ACM Transactions on Database Systems (TODS), 42(2), 1-49.
Parvaneh, A., Abbasimehr, H., & Tarokh, M. J. (2012). Integrating AHP and data mining for effective retailer segmentation based on retailer lifetime value. Journal of Optimization in Industrial Engineering, 5(11), 25-31.
Peter, M., Mofi, H., Likoko, S., Sabas, J., Mbura, R., & Mduma, N. (2025). Predicting customer subscription in bank telemarketing campaigns using ensemble learning models. Machine Learning with Applications, 100618.
Priyambada, S. A., Er, M., Yahya, B. N., & Usagawa, T. (2021). Profile-based cluster evolution analysis: Identification of migration patterns for understanding student learning behavior. IEEE Access, 9, 101718-101728.
Ramasso, E., Placet, V., & Boubakar, M. L. (2015). Unsupervised consensus clustering of acoustic emission time-series for robust damage sequence estimation in composites. IEEE Transactions on Instrumentation and Measurement, 64(12), 3297-3307.
Ramezani, F., Parvez, S., Fix, J. P., Battaglin, A., Whyte, S., Borys, N. J., & Whitaker, B. M. (2023). Automatic detection of multilayer hexagonal boron nitride in optical images using deep learning-based computer vision. Scientific Reports, 13(1), 1595.
Rousseeuw, P. J. (1987). Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of computational and applied mathematics, 20, 53-65.
Smaili, M. Y., & Hachimi, H. (2023). New RFM-D classification model for improving customer analysis and response prediction. Ain Shams Engineering Journal, 14(12), 102254.
Song, M., Zhao, X., E, H., & Ou, Z. (2016). Statistic-based CRM approach via time series segmenting RFM on large scale data. Paper presented at the Proceedings of the 9th International Conference on Utility and Cloud Computing.
Sun, Y., Liu, H., & Gao, Y. (2023). Research on customer lifetime value based on machine learning algorithms and customer relationship management analysis model. Heliyon, 9(2).
Wang, S., Sun, L., & Yu, Y. (2024). A dynamic customer segmentation approach by combining LRFMS and multivariate time series clustering. Scientific Reports, 14(1), 17491.
Wei, J. T., Lin, S.-Y., Yang, Y.-Z., & Wu, H.-H. (2019). The application of data mining and RFM model in market segmentation of a veterinary hospital. Journal of Statistics and Management Systems, 22(6), 1049-1065.
Yang, Y., & Jiang, J. (2014). HMM-based hybrid meta-clustering ensemble for temporal data. Knowledge-Based Systems, 56, 299-310.
Send comment about this article
CAPTCHA Image
Sciences and Techniques of Information Management
Volume 11, Issue 4
December 2025
Pages 56-76

Files

Share

How to cite

Statistics