Capstone project for internship with Analytics & Solutions team @ Northwell Health.
Used Python to build an automated pipeline to extract and classify data citations from research papers using LLMs.
Practiced Natural Language Processing, Named Entity Recognition, Classification, and pre/post processing of data.
Developed a predictive model for Waze to analyze user churn, using data preprocessing, feature engineering, and ML to identify key retention factors.
Delivered insights to boost engagement, reduce churn, and improve retention.
Packages: Pandas, numpy, Scipy, seaborn, Matplotlib, statsmodels, scikit-learn, xgBooost, and more.
Working in Python, analyzing + cleaning data and building a logistic regression model to analyze employee satisfaction and predict if they would leave the company or not. Designed to be presented to the HR department.
Check out my DataCamp projects, ranging from movies to agriculture to sports. Get to explore topics of interest here and have a bit of fun. EDA, Hypothesis testing, ML modeling, and more.
Web-scraping and analysis project extracting data from GoodReads using Python and Chrome Driver.