This project presents an exploratory data analysis and predictive modeling study of Zomato restaurant data. It includes data cleaning, visualization, and multiple linear regression to understand how factors such as votes, cost, and service options influence restaurant ratings. The analysis provides insights into customer preferences and key drivers of restaurant success.

This is a presentation demonstrating the nextWordPredict app for Data Science Specialisation capstone project on coursera by JHU

This project covers the full data science lifecycle in R, starting with workspace organization and data cleaning to prepare a Spotify dataset for analysis. I explored the data through visualizations and descriptive statistics to understand the distribution of musical features like energy and loudness. I then performed a correlation analysis to map how these acoustic traits relate to song popularity. Finally, I built a predictive regression model using a 70/30 training and testing split to forecast a track's success, evaluating the results through R-squared and accuracy metrics.