DILIP KUMAR UPPULA

Predicting Zomato Restaurant Ratings: A Regression Approach to Data Analysis:-

• Explored the dataset,did data preprocessing and analyzed the distribution of the target variable and identified any class imbalances.
• Descriptive and Geo-spatial Analysis was done ,determined the percentage of restaurants that offer table booking and online delivery.
• Compared the average ratings of restaurants with table booking and those without.
• Analyzed the availability of online delivery among restaurant's with different price ranges.
• Feature Engineering was done to extract additional features from the existing columns.
• Created new features like has Table booking or has online delivery by encoding categorical variables.
• Build a regression model to predict the aggregate rating of a restaurant based on available features.

outcome :-

• Lasso regression gave r2score of 0.41 ,model was overfitted so hyper parameter tuning was done to decrease ,RMSE values between train and test data.

• Pioneered the implementation of comprehensive reporting systems to meticulously track the inflow and outflow of materials, fostering heightened visibility and strategic decision-making in manufacturing operations.
• Elevated reporting standards by introducing advanced functionalities, allowing for nuanced filtration based on key parameters such as mills, heat number, grade, size, and weight, streamlining data accessibility and analysis.
• Instrumental in ensuring data integrity during the manufacturing and loading phases through the deployment of a cutting-edge heat scanner application, affirming the validity of material information in real-time.
• Introduced and optimized reporting mechanisms to meticulously monitor material flow, while concurrently overseeing the implementation of a robust heat scanner application to detect and rectify any defects in materials during manufacturing and loading.