It is an AI-powered machine learning project designed to simplify restaurant discovery by recommending restaurants with similar characteristics. Instead of relying on user ratings or purchase history, the system analyses restaurant information, including cuisine, location, pricing, ratings, dining offers, and available services, to generate accurate recommendations.

The recommendation engine is built using a Content-Based Filtering approach. Restaurant profiles are created by combining important textual and categorical features, which are then transformed into numerical vectors using TF-IDF Vectorisation. The similarity between restaurants is computed using Cosine Similarity, enabling the system to suggest restaurants that closely match the selected restaurant.

To make the system interactive and user-friendly, the project is deployed using Streamlit, providing a clean web interface where users can search restaurants and refine recommendations through multiple filters, including location, food preference, ratings, maximum budget, home delivery availability, and dining offers.

The project demonstrates the practical application of recommendation systems widely used by platforms such as Zomato, Swiggy, Netflix, Amazon, and Spotify. It also showcases the complete machine learning workflow, including data preprocessing, exploratory data analysis (EDA), feature engineering, text vectorization, similarity computation, and deployment.

Technology Used