This project, an individual assignment for MIS772 Predictive Analytics, focuses on analyzing Zomato restaurant data to provide insights and develop predictive models using RapidMiner. The project aims to address the Bangalore Food Assist's (BFA) needs by clustering restaurants based on customer feedback, identifying review differences across meal types, and creating an estimation model for predicting restaurant ratings. The student utilized techniques such as data exploration, cleaning, and model creation with classifiers like Random Forest and neural nets. The analysis includes the creation of correlation matrices, model evaluation, and improvement using performance operators. The final solution integrates these components to offer a comprehensive understanding of the data and provide actionable recommendations for BFA, focusing on high precision of estimates measured in MAE, RMSE, and correlation. The project provides a detailed overview of the methodologies, results, and the iterative process of model refinement within the RapidMiner environment.
![[object Object]](/_next/static/media/star-bottom.7253800d.svg)
