Skip to content
View yougijain's full-sized avatar
3 followers · 3 following

Achievements

Achievement: Pull Sharkx2Achievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: YOLO

Achievements

Achievement: Pull Sharkx2Achievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: YOLO

Block or report yougijain

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
yougijain/README.md

Hi, I'm Yougi

Informatics & Psychology @ UMass Amherst '27 · SQL + Python for experiments, pipelines, and dashboards.

  • 🔬 When Average Effects Lie: causal uplift modeling on a 64K-customer email experiment (targeting one campaign adds $16.95/1,000 customers, the other shows no signal and shouldn't be deployed)
  • 📊 NYC Collisions: injury-risk model over 637K NYC crash records, self-refreshing weekly via GitHub Actions, ranks 1,093 intersections by excess injury risk
  • ⚙️ LineLab: full-stack Monte Carlo strategy app

Portfolio LinkedIn Email

Pinned Loading

  1. NYC-Collisions NYC-Collisions Public

    Finds NYC intersections where people get hurt more often than the crashes there would predict. 637K records, pipeline refreshes itself weekly, and a live dashboard.

    Python

  2. When-Average-Effects-Lie When-Average-Effects-Lie Public

    Using causal inference and statistics to show that two email campaigns that look equally successful need opposite strategies. 64,000-customer randomized trial.

    Python

  3. spotify-listening-analysis spotify-listening-analysis Public

    SQL-first (DuckDB) analysis of Spotify listening behavior: sessionization, cohort retention, taste concentration, and a hypothesis test.

    Jupyter Notebook

  4. seed-miner seed-miner Public

    Scheduled GitHub Actions pipeline that generates LLM project ideas and re-weights sampling from human review feedback

    Python

  5. LineLab LineLab Public

    Full-stack strategy trainer: Next.js frontend on a FastAPI Monte Carlo simulation engine

    TypeScript