Journal of Digital Business and Data Science

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

Anton Budiyono — 2025-12-29

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

Ahmad Lukman Nugraha — 2025-12-29

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.

The Influence of Customer Ratings and Reviews on Online Electronic Product Purchase Decisions

Asep Nugraha — 2026-01-03

The rapid growth of e-commerce has created information asymmetry challenges, as consumers cannot physically inspect products before purchasing. Customer ratings and reviews, as forms of electronic word-of-mouth (eWOM), have emerged as critical information sources, yet their specific influence on Indonesian consumers remains underexplored. This study aims to analyze the influence of customer ratings and reviews on online purchase decisions for electronic products in Indonesia's e-commerce platforms. Using a quantitative approach, data were collected from 280 respondents through an online survey with Likert scale questionnaires. Data analysis utilized multiple linear regression with SPSS 25.0, including validity and reliability tests (Cronbach's Alpha), classical assumption tests (Kolmogorov-Smirnov, VIF, Tolerance, Glejser, linearity), partial hypothesis testing (t-test), simultaneous hypothesis testing (F-test), and coefficient of determination (R²).The results indicate that customer ratings significantly influence purchase decisions (t = 5.847, p < 0.05), customer reviews have an even stronger influence (t = 8.329, p < 0.05), and both variables simultaneously show significant influence (F = 64.238, p < 0.05) with R² = 0.315. These findings confirm that eWOM serves as a critical component in Indonesian consumers' decision-making process for purchasing electronic products online, with important implications for e-commerce platforms and digital marketing strategies.

The Effect of Service Quality, Products, Transaction Security, and Ease of Use of the Platform on Customer Satisfaction in E-Commerce

Nita Anggreyani — 2026-01-03

Data was collected through a survey involving 200 respondents (100 consumers and 100 entrepreneurs) from users of e-commerce platforms in Indonesia. Multiple linear regression analysis was employed to examine the relationships between variablesin building customer trust and supporting satisfaction. Overall, the results of this study confirm that to create a satisfying shopping experience, e-commerce companies must pay attention to the balance between service quality, product, ease of use, and transaction security. The results of this study also show that customer trust in transaction security is an important factor that should not be ignored in increasing customer satisfaction and loyalty. Therefore, e-commerce companies need to invest in better security systems and transparent policies to protect customers' personal data and ensure smooth transactions.

Case Study of the Application of Digital Marketing in Increasing the Competitiveness of MSMEs in the Industrial Era 4.0

Frilla Gunariah — 2026-01-03

This study aims to analyze the application of digital marketing in increasing the competitiveness of MSMEs in Indonesia, focusing on three MSME actors in various sectors: culinary, handicrafts, and retail. Through in-depth interviews, it was found that digital marketing has a positive impact on product visibility, market reach, and interaction with customers. Social media platforms such as Instagram, Facebook, and marketplaces such as Shopee and Tokopedia allow MSMEs to reach a wider range of consumers, reduce marketing costs, and increase sales. However, the challenges faced by MSMEs include price competition in the marketplace, limited human resources in digital marketing management, and consistency in content creation. This study concludes that the success of the implementation of digital marketing is highly dependent on internal readiness, technology access, and planned strategies. Therefore, MSME actors need to strengthen their digital capabilities through more efficient training and resource management to maximize the potential of digital marketing and strengthen competitiveness in an increasingly competitive global market. The research provides practical implications for MSME practitioners in formulating adaptive digital strategies, for policymakers in designing targeted digital literacy programs, and for business incubators in developing sector-specific mentoring frameworks to enhance the digital competitiveness of Indonesian MSMEs.