E-Commerce Product Recommendation System Using Case-Based Reasoning (CBR) and K-Means Clustering

Abstract

This research proposes and implements an e-commerce product recommendation system that combines Case-Based Reasoning (CBR) and K-Means Clustering algorithms. The main aim of this research is to provide more personalized and relevant product recommendations to e-commerce users. The CBR approach leverages users' transaction history to provide customized recommendations, whereas K-Means Clustering groups users with similar preferences increase the relevance of recommendations. This study assesses the effectiveness of the system by conducting a comprehensive evaluation by comparing system recommendations with actual user preferences. The results of this study reveal that the combined approach of CBR and K-Means Clustering can improve the performance of e-commerce product recommendations, ensure the accuracy of recommendations, and produce a more satisfying shopping experience for users. Although there are limitations in terms of the dataset used and the choice of algorithm parameters, this research makes an important contribution in developing a more adaptive and personalized recommendation system for e-commerce platforms.