Sahittyam Nag

Seasoned collaborator experienced in meeting needs, improving processes and exceeding requirements in team environments. Diligent worker with strong communication and task prioritization skills. Organized and dependable candidate successful at managing multiple priorities with a positive attitude. Willingness to take on added responsibilities to meet team goals.

Sentiment Based Recommendation System I Tech Stack : Python I 09/01/23 :

• Building a recommendation system for products based on consumers sentiments and reviews. Designed a user and item based recommendation using collaborative filtering for Users, items, and content to suggest better recommendations and also deploying the model with help of FASTAPI.

Identifying Entities in Healthcare Data I Tech Stack : Python, 10/01/22 : 

• Build an algorithm to map the diseases and their respective treatment.
• Defined features for CRF and build the CRF model with the f1 Score being 91% which is decent.

Predictive Model for Demand of Bike Sharing I Tech Stack : Python I 09/01/22 : 

• Required to model the demand for shared bikes with the available independent variables. It will be used by the management to understand how exactly the demands vary with different features.
• Build a linear regression model with the significant variables and no multi-collinearity as the model chosen has all VIF values less than 5.

Automatic Ticket Classification I Tech Stack : Python I 11/01/22 :

• Building an ML model that is able to classify tickets automatically based on consumer complaints/reviews to help pipeline these tickets to the respective categories to provide quick and easy resolution.
• Data pre-processing steps are done using statistical operations like Lemmatization & POS tagging.
• Topic Modelling was done using NMF and created supervised model were used to train the data.
• Developed a model with an Accuracy score of 92%.

IMDB Movie Analysis I Tech Stack : SQL I 08/01/22 : 

• Identifying the Dominating Directors in the market, Preference of genre and Selection of priority actors and actresses.
• Finding the most and least top 20 Directors based on their ratings, gross earnings, reviews and ratings.
• Filter the generation and finding the most watched movies.
• Sentiment Analysis of the movie descriptions.
• Also identifying the most worked stars together ratings wise, gross earnings and vote count.