2nd-year B.Tech CSE student building a hands-on ML/DS portfolio — from web-scraped datasets to prediction models, one project at a time.
I'm a Computer Science undergrad focused on data science and machine learning, currently building a portfolio aimed at internships in the field. I like projects that go from a messy CSV to a working, presentable result.
Outside of notebooks, I explore content creation and enjoy the intersection of data storytelling and creativity — the same instinct that makes me care about how a project looks, not just how it performs.
The stack behind every project on this page — from data cleaning to deployment.
Each one shipped with a notebook, a README, and a clear takeaway.
Analyzed 32K+ horror movies across decades and built a Random Forest model to predict box office revenue, with a live interactive predictor built on ipywidgets.
View on GitHub ↗Logistic Regression model predicting student outcomes, deployed as a live Streamlit app.
View on GitHub ↗Scraped 1000 books across nested detail pages from books.toscrape.com, handling encoding edge cases along the way.
View on GitHub ↗Pulled and visualized stats for 50 Pokémon via a public API — five charts, one clean notebook.
View on GitHub ↗