Restaurants across the world receive ratings from thousands of customers on Zomato, reflecting factors like cuisine type, price range, delivery options, and overall experience.
Understanding what drives these ratings can help businesses enhance customer satisfaction and improve their performance.

In this competition, your task is to predict the average restaurant rating (Aggregate rating) based on various features such as location, cuisines, price range, country, and services offered.
Participants will use the provided dataset (Zomato + Country Code) to build a machine learning regression model capable of accurately estimating restaurant ratings.

The competition is open exclusively to ABES Engineering College students and faculty and will run for 24 hours.
After the competition ends, all participants’ performances will be displayed on a Kaggle leaderboard, which faculty members can review to assess results.

Objective:
Build a model to predict the Aggregate rating of a restaurant using features like Cuisines, Price range, Votes, and service availability.

Evaluation Metric:
Submissions are evaluated based on Root Mean Squared Error (RMSE) between predicted and actual ratings.