CUSTOMER SUPPORT CHATBOT

This paper presents the development of an AI-based customer support chatbot using natural language processing (NLP) and deep learning models. The chatbot is designed to automatically respond to frequently asked customer queries using a pre-trained transformer model from Hugging Face. The system utilizes a curated dataset of common customer service questions and answers, fine-tunes a DistilBERT model for question-answering tasks, and integrates with a Gradio-based web UI for real-time interaction. The objective is to enhance customer experience by offering quick, reliable, and automated assistance. This paper outlines the methodology, model selection, data preparation, testing, and deployment processes. The chatbot achieved high accuracy and response confidence on common queries, proving its efficacy for customer service applications.