8000
Skip to content
View hugomagee's full-sized avatar

Highlights

  • Pro

Block or report hugomagee

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
hugomagee/README.md

Hugo Magee

Machine learning for data science, athletic performance, and quantitative finance.

GTM Systems & Analytics Intern @ FundRecs · BSc Science, University College Dublin (2026) · International 400m sprinter for Ireland (PB 46.95s).

Featured projects

  • medalist — Harness for AI agents to autonomously solve tabular data-science competitions end-to-end; live agent placed top ~16% (est.) on a finished Kaggle Playground competition with zero human involvement.
  • OptimalAthlete — ML system predicting 400m sprint times (R²=0.84), trained on 18 months of personal race and training data.
  • GrowthHog — Systematic equity screener for 170+ global tickers: lifecycle-aware scoring, sector health, insider tracking, and portfolio optimisation, running weekly via cron on Polygon.io data.
  • TradeMetrics — Pairs trading and portfolio analytics system (Sharpe 1.35), built on 12 months of Interactive Brokers data.
  • HorseLay (private) — Automated lay-betting system for the Betfair exchange: price-shortening signal on flat racing, full backtesting engine, and live bot. Backtested on GB/IE/FR data across 2015–2024 (90.9% strike rate, small validated sample).

Tech stack

Python · R · SQL · scikit-learn · XGBoost · Streamlit

Contact

LinkedIn · hugomagee2002@gmail.com

Pinned Loading

  1. OptimalAthlete OptimalAthlete Public

    ML pipeline for 400m sprint performance — Streamlit dashboard, walk-forward validation, and an honest statistical re-audit of its own headline claims

    Jupyter Notebook 2

  2. medalist medalist Public

    Harness for AI agents to autonomously solve tabular data-science competitions end-to-end

    Python

  3. TradeMetrics TradeMetrics Public

    Pairs trading & portfolio analytics system — Sharpe 1.35, built on 12 months of Interactive Brokers data

    Python

  4. GrowthHog GrowthHog Public

    Systematic equity screener for 170+ global tickers — lifecycle-aware scoring, sector health, insider tracking, portfolio optimisation

    Python 1

0