Enhancing E-commerce Fashion Sales through Personalized Recommendation Systems

Personalized recommendation systems are pivotal in the thriving e-commerce fashion sector, enriching customer experiences and driving sales. This paper introduces an innovative method to enhance e-commerce fashion sales through personalized recommendations. The model merges Singular Value Decomposition (SVD) Reranking with customer grouping, yielding tailored product suggestions for distinct customer segments. The study comprehensively explores multiple recommendation techniques, assessing their performance using Mean Average Precision (MAP) scores. Results demonstrate the superiority of the proposed model, achieving a validation score of 0.032007. This success is attributed to the model’s ability to capture latent features and offer personalized suggestions based on customer group traits. This research underscores the significance of personalized recommendations in boosting ecommerce fashion sales. The proposed approach, SVD Reranking with customer grouping, excels in providing personalized suggestions across diverse customer segments. These findings contribute to the advancement of recommendation systems in fashion, fostering customer satisfaction, minimizing returns, and bolstering sustainability.