• Collaborated and analyzed a dataset containing loan data from the lending club website using univariate and bivariate analysis.• Contributed to the development of a credit scoring model that can differentiate between good and bad loans.• Screened the variables using Weight of Evidence (WOE) and Information Value (IV) for required features.• Developed a python package to contain all functions required for carrying out exploratory data analysis.

• Independently developed Book Recommendation Engine based on Google Book API and parameterized equation scores to provide recommendations to book enthusiasts• Revamped the product's recommendation algorithm by visualizing and studying attributes most relevant to providing recommendations• Also, Applied NLP techniques in conjunction with the final pivot table and K-nearest Neighbors for collaborative filtering recommendations.• Decreased response time in the backend of the previous model by switching to a self-constructed content-based recommendation engine using data from the Goodreads platform.• Parallelly, applied Amazon Rekognition and OpenCV with S3 bucket to create emotion-based, color-changing bounding boxes around video frames as input