E-commerce customer churn prevention using machine learning-based business intelligence strategy

Abstract

Businesses in the E-Commerce sector, especially those in the business-to-consumer segment, are engaged in fierce competition for survival, trying to gain access to their rivals' client bases while keeping current customers from defecting. The cost of acquiring new customers is rising as more competitors join the market with significant upfront expenditures and cutting-edge penetration strategies, making client retention essential for these organizations. The best course of action in this circumstance is to detect prospective churning customers and prevent churn with temporary retention measures. It's also essential to understand why the customer decided to go away to apply customized win-back strategies. Each customer's information, including searches made, purchases made, frequency of purchases, reviews left, feedback is given, and other data, is kept on file by the e-commerce company. Machine learning and data mining may be aided by examining this enormous quantity of data, analysing customer behaviour, and seeing potential attrition opportunities. The support vector machine is a popular supervised learning method in machine learning applications. Predictive analysis uses the hybrid classification approach to address the regression and classification issues. The process for forecasting E-Commerce customer attrition based on support vector machines is presented in this paper, along with a hybrid recommendation strategy for targeted retention initiatives. You may prevent future customer churn by suggesting reasonable offers or services. The empirical findings demonstrate a considerable increase in the coverage ratio, hit ratio, lift degree, precision rate, and other metrics using the integrated forecasting model. To effectively identify separate groups of lost customers and create a customer churn retention strategy, categorize the various lost customer types using the RFM principle.