AI-BASED PRODUCT RECOMMENDATION SYSTEM WITH CONVERSATIONAL CHATBOT

Abstract

This thesis presents an AI-based product recommendation system integrated with a conversational chatbot aimed at enhancing the online shopping experience. With the rapid growth of e-commerce platforms, users are often overwhelmed by the vast number of available products. To address this challenge, the proposed system leverages machine learning techniques to analyze user preferences, product attributes, and historical interaction data to generate personalized recommendations. The system consists of two main components: a recommendation engine and a chatbot interface. The recommendation module processes product datasets and applies filtering techniques such as content-based and collaborative filtering to suggest relevant products based on user interests and queries. The chatbot component provides a conversational interface that allows users to interact naturally with the system, ask product-related questions, and receive guidance throughout their shopping journey. The integration of the chatbot enhances user engagement by providing real-time assistance and improving accessibility. The system is designed to ensure accuracy, efficiency, and ease of implementation, making it suitable for practical deployment in e-commerce applications. Experimental results demonstrate that the proposed system effectively delivers relevant product recommendations while improving user interaction and satisfaction. This approach highlights the potential of combining artificial intelligence and conversational interfaces to create smarter and more user-friendly shopping platforms.