Streamlining Grocery Shopping : Personalized Recommendations for Enhanced Cart Performance

Abstract

In the burgeoning landscape of e-commerce, the demand for personalized user experiences has become paramount. Traditional methods of online shopping often require users to manually select products for their carts, resulting in a time-consuming and often inaccurate process. In response, this paper presents ShopSculpt, an innovative approach to cart creation that leverages intelligent algorithms to automate product selection based on user interests, profile details, seasonal trends, and weather conditions. Through the integration of predictive modeling and recommendation systems, ShopSculpt aims to streamline the shopping experience, enhancing user satisfaction and engagement. This paper outlines the methodology behind ShopSculpt, presents experimental results demonstrating its efficacy, and discusses its implications for the future of e-commerce. A primary challenge with online shopping is the lack of personalized assistance akin to that found in physical stores. In physical supermarkets, items frequently purchased together are grouped together, encouraging consumers to make additional purchases and thereby boosting sales. We've incorporated this principle into our e-grocery system to create a platform that suggests items to users that they might not have considered previously. Through our efforts, we've established a robust recommendation framework leveraging the Apriori Algorithm for association rule mining and Collaborative Filtering employing the Nearest Neighbors algorithm. We've pinpointed four primary scenarios, encompassing recommendations based on past purchase histories, similarities with other users' preferences, items currently in the user's cart, and top-rated products within the grocery category. This multifaceted approach ensures that our recommendations are tailored to each user's unique needs and preferences.