SWORAJKHADKA
Data Analyst·ML Engineer·Software Engineer
Building products at the intersection of clean engineering and intelligent data.
At the intersection of engineering & data.
I'm a Full Stack Developer and Data Science enthusiast based in Nepal, passionate about crafting products that sit at the intersection of clean engineering and intelligent data. I enjoy building end-to-end systems — from database schema to polished UI.
On the data side, I work with Python, Pandas, and Scikit-learn to explore datasets, build predictive models, and surface insights that drive real decisions. I believe great software doesn't just work — it tells a story.
When I'm not coding I'm reading about machine learning research, contributing to side projects, or finding new ways to make complex ideas feel simple.
Clean Code
Readable, maintainable systems with clear structure and sensible abstractions.
Data-Driven
Decisions backed by data — from user analytics to ML-powered insights.
Always Learning
Continuously exploring new tools, frameworks, and research to stay sharp.
The stack behind the work.
30+ tools I reach for — grouped by what they let me build.
Showing 42 · All
Things I've built.
A cross-section of full-stack products, ML experiments, and data explorations.
Scash
A web platform where users can publish their side hustles and monetize their skills in exchange for payment.
AI Lost and Found
Full-stack AI platform for campus use — integrates Google Gemini to extract semantic keywords from natural language descriptions and ranks lost/found item matches via a custom 0–100 scoring algorithm in MongoDB.
GitHub Profile Analyzer
View detailed GitHub profile statistics — repos, stars, languages, and contribution graphs from just a username.
Chalchitra
Content-based movie recommendation engine using TF-IDF vectorization and cosine similarity across 5,000 movies, with Bayesian-weighted aggregation of IMDb, Rotten Tomatoes, and Metacritic scores.
Customer Segmentation & Retention Analysis
End-to-end analytics pipeline on UCI Online Retail II using RFM scoring and KMeans clustering to classify customers into 4 behavioral tiers, with a Logistic Regression churn model deployed as an interactive Streamlit dashboard.
Public signals.
Live pulls from GitHub and LeetCode — refreshed hourly.
GitHub
LeetCode
Let's make something.
Have a project in mind or just want to say hi? My inbox is always open.
I'm open to freelance, contract, and full-time roles — especially at the intersection of data and product. Or reach me directly:
sworajkhadka21@gmail.com