A STUDY ON CROSS-SELLING STRATEGIES IN E-COMMERCE PLATFORMS BASED ON COLLABORATIVE FILTERING AND ASSOCIATION RULES

Abstract

This study investigates the application of cross-selling strategies in e-commerce platforms by integrating collaborative filtering and association rule mining techniques. With the rapid expansion of e-commerce, personalized product recommendations have become essential for enhancing customer engagement and increasing sales revenue. The primary objective of this research is to design and evaluate a hybrid model that combines collaborative filtering, which identifies user preferences based on historical behavior, with association rule mining, which uncovers frequent co-purchased items. Using a real-world transactional dataset from an e-commerce platform, the proposed model was implemented and tested. The findings reveal that the hybrid approach significantly improves recommendation accuracy and cross-selling performance compared to using either method in isolation. Key outcomes include higher click-through rates, increased average order values, and enhanced customer satisfaction. This research underscores the practical value of integrating multiple data-driven techniques to optimize cross-selling strategies, offering actionable insights for e-commerce businesses seeking to leverage big data for competitive advantage.