Improved recommender system using Neural Network Collaborative Filtering (NNCF) for E-commerce cosmetic product

Abstract

This study presents an enhanced recommender system tailored for e-commerce platforms specializing in cosmetic products. Traditional recommender systems often need help providing accurate and personalized recommendations due to the complexity and subjectivity inherent in cosmetic preferences. In e-commerce, personalized product recommendations are crucial to improving user engagement and driving sales. This paper presents an innovative approach to enhance recommendation systems by leveraging neural network collaborative filtering techniques for the cosmetic product domain. The proposed method integrates neural networks into collaborative filtering, namely neural network collaborative filtering with improved preprocessing step. To validate the effectiveness of our proposed system, extensive experiments were conducted using real-world e-commerce cosmetic datasets "eCommerce Event History in Cosmetics Shop".   Additionally, we evaluate the system's performance using historical e-commerce event data in cosmetics stores, demonstrating the system's effectiveness with mean reciprocal ratings (MRR) and normalized discount cumulative gain (NDCG). Evaluation Metrics of MRR and NDCG in this study got 0.56 and 0.60, respectively, with a split of the data: 70% train data, 15% validation data, and 15% test data. This study obtained better evaluation metrics than the previous study, which had an MRR of 0.31 and NDGC of 0.32. Furthermore, this model exhibits robustness against data sparsity and cold-start problems commonly encountered in e-commerce platforms. This research advances knowledge of recommendation systems and paves the way for more personalized and efficient online shopping experiences.