Skip to content
View Gaze31's full-sized avatar

Block or report Gaze31

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.

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
Gaze31/README.md

Hi, I'm Sumedha 👋

Quant-Minded ML Engineer | Python Full-Stack Developer

I build models that survive walk-forward testing — then ship them as real APIs and dashboards. Not notebooks. Production.


📈 Quant / Finance work

  • 🔀 3 merged PRs to yfinance — a 22k★ production library, actual maintainer-reviewed code
  • 📊 Alpha Engine — multi-factor model on Nifty 50, Sharpe 5.87, walk-forward validated with Deflated Sharpe Ratio
  • 🎲 Derivatives Pricing Engine — Black-Scholes, Binomial CRR, Monte Carlo (100K paths); put-call parity verified to 0.000000
  • 🧠 FinBERT Sentiment Pipeline — 0.96 Macro F1, 4-stage NLP pipeline, stress-tested on live headlines

🖥️ Full-stack / ML engineering work

  • 🏦 Credit Risk API — gradient boosting (0.77 AUC), calibrated probabilities, serverless FastAPI on Vercel, React dashboard
  • 🔗 Live, working endpoint — hit it right now, it's real
  • 🐳 Model training → REST API → Postgres → React UI → containerized deploy

🛠️ Stack


📊 GitHub Stats


🔍 Currently

Open to quant/ML engineering roles — remote, globally.

Pinned Loading

  1. alpha-engine alpha-engine Public

    Multi-factor alpha engine on Nifty 50 — momentum & mean-reversion factors. Sharpe 5.87, 146% return. Walk-forward validation, Deflated Sharpe Ratio.

    Jupyter Notebook

  2. credit-risk-api credit-risk-api Public

    End-to-end credit risk ML system — gradient boosting model (0.77 AUC) with calibrated probabilities, numpy-only serverless inference on FastAPI/Vercel, React dashboard.

    Python