Journal of Digital Business and Data Science

Customer Churn Prediction Uses Machine Learning to Improve Retention on Digital Platforms

2025-12-09T02:26:39+00:00

Customer churn is a critical challenge for digital platforms operating in highly competitive markets such as e-commerce. This study aims to develop a machine learning–based predictive model to identify Shopee customers in Indonesia who are at high risk of churn, using behavioral and transactional data. A supervised learning approach was employed using multiple algorithms, including Logistic Regression, Decision Trees, Random Forests, and XGBoost. The dataset consisted of user activities, including transaction frequency, recency, voucher usage, application session count, and interaction with promotional features. Data imbalance was addressed using the SMOTE technique to improve classification stability. Results showed that XGBoost achieved the best performance across all evaluation metrics, with an AUC of 0.948, indicating strong discriminative ability. Feature importance analysis revealed that recency, transaction frequency, voucher usage rate, and app session frequency were the most influential predictors of churn. These variables indicate declining engagement and reduced responsiveness to promotional incentives, which are key behavioral signals of churn. The study contributes to both academic literature and practical applications by demonstrating how behavioral analytics and machine learning can support early churn detection and inform targeted retention strategies. Implementing such predictive systems can help e-commerce platforms optimize customer lifetime value and reduce revenue loss.

The Role of Transaction Security Perception in Reducing the Risk of Churn for E-Wallet Users in Indonesia

2025-12-09T02:46:35+00:00

The development of e-wallet services in Indonesia shows rapid growth, but the high competition between players and the increase in digital crime cases pose a significant potential for churn. This study aims to analyze the influence of transaction security perception on the risk of churn in e-wallet users in Indonesia. The research method used a quantitative approach with a survey technique of 428 respondents who actively used e-wallet services. Data analysis was carried out through validity, reliability, and simple linear regression tests. The results showed that the perception of transaction security had a negative and significant effect on churn risk, with a regression coefficient value of -0.649 and a significance of <0.001. These findings confirm that the higher the perceived perception of security by users, the lower their tendency to move to another platform. An R² value of 0.421 indicates that the perception of security is able to explain a substantial proportion of the variation in churn risk. The study also identified that other factors such as digital service quality, user experience, feature innovation, promotion, and company reputation also influence churn behavior. The implications of this study underscore the importance of improving system security, privacy policy transparency, user education, and a comprehensive retention strategy in maintaining the loyalty of e-wallet users amid increasingly fierce industry competition.