Sentiment Analysis on Amazon Fine Food Reviwes Dataset

Used all popular classification algorithms with hyperparameter tuning. For feature transformation I have used :

Financial Distress Prediction using SMOTE

Detailed analysis and explaining the working of SMOTE techniques for imbalanced datasets :

Human Activity Recognition using smartphone

Detailed analysis of Human Activity Recognition using svm :

Netflix Movie Recommendation System

Netflix provided a lot of anonymous rating data, and a prediction accuracy bar that is 10% better than what Cinematch can do on the same training data set. (Accuracy is a measurement of how closely predicted ratings of movies match subsequent actual ratings.)

• Predict the rating that a user would give to a movie that he has not yet rated.
• Minimize the difference between predicted and actual rating (RMSE and MAPE)

Neural Style transfer

I have used pre trained models and converted this image to this beautiful art. Click on details for better explanation of this project

Mahindra First Choice Services

Identifying the ownership pattern of cars throughout the country. This also captures the problem wherein information regarding the spending patterns can be identified. A detailed analysis of car make and model, time and type of services etc vary with location. The servicing industry is local in nature, so this kind of analysis rendered some really interesting business insights.

Customer Lifetime value prediction: Revenue Forecast - Times Series Analysis with ARIMA.