Skip to content
View asoracca's full-sized avatar

Block or report asoracca

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
asoracca/README.md

Hi, I'm Anggun 👋

Quant-minded software builder working at the intersection of markets and code — from stochastic-volatility models to shipped, full-stack products. I like building things that are both rigorous and real.

🎯 Seeking a Summer 2027 Software Engineering internship · open to quant / fintech too 🧰 Python · TypeScript · React/Next.js · Postgres · a healthy obsession with validating my own work


🚀 Featured Projects

📈 TradeGoons — full-stack AI trading app (shipped & live)

A paper- and real-trading journal with live market data, AI coaching, options chains, portfolio analytics, and a risk-visualizing UI. Installable as a phone app. Stack: Next.js · TypeScript · Prisma · Supabase (Postgres) · Vercel · Gemini API

🌊 soxl-vol-surface — options volatility research

IV rank & percentile signals, GARCH volatility forecasting, Black-Scholes Greeks, a 3D volatility surface, and a Heston stochastic-volatility model that reproduces the implied-vol smile a constant-vol model can't.

🔬 momentum-factor-backtest — strategies + honest validation

A cross-sectional momentum backtest, then the part most people skip: a Fama-French factor regression (which showed the strategy has no alpha — just momentum-factor exposure) and a cointegration pairs stat-arb study validated with out-of-sample splits, transaction costs, and a multiple-testing correction.

🛡️ leveraged-etf-risk-lab — portfolio risk analytics

Sharpe/Sortino, beta, drawdown, and stress tests for a leveraged-ETF book, plus a Hidden Markov Model that classifies the market into bull/bear regimes from return patterns alone.

🛰️ new-space-radar — event study

Measures cumulative abnormal returns (CAR) around launches and contract news for space-sector equities, with significance testing.


🧠 How I work

  • Build strategies and try to break them. A pretty backtest is the start of due diligence, not the end — out-of-sample tests, cost modeling, and multiple-testing corrections are non-negotiable.
  • Ship fast, then harden. I use modern AI tooling to move quickly, then dig into the code so I actually understand what I shipped.
  • Make it legible. Every repo has a README that explains the why, the method, and the result.

🛠️ Tech

Python · pandas · NumPy · statsmodels · SciPy · TypeScript · React · Next.js · Prisma · PostgreSQL · Supabase · Vercel · Git

📫 Reach me

Pinned Loading

  1. soxl-vol-surface soxl-vol-surface Public

    Options volatility dashboard and put-selling signal research for SOXL.

    Python 1

  2. redline-exchange redline-exchange Public

    Python

  3. pokeringdumdum pokeringdumdum Public

    A not-so-dumb poker game-theory lab using CFR and CFR+.

    Python

  4. backtest-engine backtest-engine Public

    Python