AI-Based Repurchase Prediction in Retail Customer Behavior Analysis

This study explores the application of artificial intelligence–driven analytics in predicting customer repurchase behavior, enhancing customer value management, and strengthening the competitiveness of automotive department store chains in a rapidly evolving retail environment. Transaction data collected from an automotive retailer’s POS system was analyzed using the RFM (Recency, Frequency, Monetary) model to segment customers and classify them according to value. Through this approach, customers were categorized into distinct value tiers to better understand their purchasing behaviors and loyalty tendencies. The analytical results indicate that RFM-based segmentation effectively distinguishes high-, medium-, and low-value customers, thereby supporting the formulation of targeted retention and engagement strategies. Moreover, variations in repurchase intentions, purchasing frequencies, and spending levels across customer groups highlight the necessity of adopting differentiated marketing and communication approaches. Beyond descriptive segmentation, the study further demonstrates that AI-enabled predictive modeling can generate actionable insights for anticipating future customer behavior, developing personalized and data-driven marketing strategies, optimizing product–service portfolios, and ultimately fostering sustainable business growth and competitive advantage for automotive retail enterprises.