Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{198220,
        author = {Prof Dr. S.L. Gupta},
        title = {A Study on Enhancing Customer Reactivation through RFM Analysis and Predictive Analytics},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {13575-13593},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198220},
        abstract = {Understanding consumer behavior and making accurate predictions about their propensity to return are essential for increasing customer lifetime value and retention in the cutthroat world of contemporary retail. Despite being a popular technique for determining customer value, the traditional Recency, Frequency, and Monetary (RFM) analysis frequently fails in dynamic markets because it relies on rule-based models and static clustering techniques that do not support customized marketing strategies. These restrictions lead to the treatment of consumer segmentation and reactivation as distinct procedures, which lowers the efficacy of marketing as a whole. This research combines RFM analysis with Random Forest classification and K-Means clustering to provide a data-driven, integrated approach that improves client reactivation efforts. The method uses unsupervised K-Means clustering to first divide up the customer base according to their buying patterns. Then, it uses the cluster characteristics that are produced in a supervised Random Forest model to forecast the chance that inactive customers would reactivate. A more sophisticated and predictive knowledge of consumer dynamics is guaranteed by the model's integration of the advantages of supervised and unsupervised learning. When applied to a real- world retail dataset, the framework demonstrated a great clustering performance, exhibiting meaningful and well-separated clusters with a Calinski-Harabasz Index of 14,913.66 and a Silhouette Score of 0.5524. Furthermore, 97.8% classification accuracy and zero misclassifications were attained by the prediction model on the test set, indicating its practical applicability and resilience. The creation of more focused and successful marketing campaigns is made possible by this thorough technique, which closes the gap between client segmentation and reactivation forecast. Finally, by assisting in the creation of intelligent CRM (Customer Relationship Management) systems that maximize marketing budgets and enhance customer retention through prompt and tailored re-engagement campaigns, the research provides a promising avenue for further research in predictive customer analytics.},
        keywords = {Customer Reactivation, RFM Analysis, Customer Segmentation, K-Means Clustering, Random Forest Classifier, Predictive Analytics.},
        month = {April},
        }