Apparel Recommendation System using Rule based Filtering and SMOTE for Online Shopping

The Apparel Recommendation System (ARS) is a machine learning-based platform designed to enhance the shopping experience by providing personalized apparel suggestions based on user preferences such as type, color, price range, and ratings. The user interface, developed with Tkinter, is simple and interactive, allowing effortless selections through drop-down menus and sliders. On the backend, SMOTE (Synthetic Minority Over-sampling Technique) addresses dataset imbalances, ensuring fair representation across apparel categories. A rule-based filtering approach aligns recommendations with user-selected preferences, resulting in accurate suggestions. Additionally, a live chat feature, integrated with React.js, Node.js, and Socket.io, offers real-time assistance. The curated dataset improves recommendation accuracy, enabling users to quickly find apparel that matches their individual styles.