|
AUTHOR(S): Mitra Penmetsa, Jayakeshav Reddy Bhumireddy, Rajiv Chalasani, Mukund Sai Vikram Tyagadurgam, Venkataswamy Naidu Gangineni, Sriram Pabbineedi
|
TITLE |
 PDF |
ABSTRACT Customer retention is one of the most critical concerns for businesses. Businesses try to decrease customer turnover in order to maximize client lifetime value while lowering the cost of acquiring new customers. By focusing on customer churn prediction and identification, organizations can foresee which customers are most likely to depart. This enables them to implement customized, pertinent actions to lower the rate of client attrition. This paper suggests a machine learning (ML)-based approach that makes use of Random Forest (RF) to predict customer attrition in e-commerce platforms. Recall, accuracy, precision, F1-score, and ROC-AUC were among the metrics used to evaluate the Random Forest model, which demonstrated an impressive accuracy of 95%, a precision of 98%, and a ROC-AUC of 98.51%. Random Forest was shown to be the most successful prediction method based on comparison tests with decision trees (DT) and support vector machines (SVM). With the use of real-time datasets, deep learning techniques, and large-scale deployment for e-commerce enterprises, these results confirm the efficacy of ensemble learning approaches in customer retention activities. |
KEYWORDS E-commerce, big data, Customer churn, Customer retention, Predictive analytics, Machine learning, E-commerce Customer Churn data |
|
Cite this paper Mitra Penmetsa, Jayakeshav Reddy Bhumireddy, Rajiv Chalasani, Mukund Sai Vikram Tyagadurgam, Venkataswamy Naidu Gangineni, Sriram Pabbineedi. (2025) Big Data and Predictive Analytics for Customer Retention: Exploring the Role of Machine Learning in E-Commerce. International Journal of Computers, 10, 260-267 |
|
