Research and practical education for traders, quantitative researchers, and Python developers. Learn to build and test trading systems, evaluate strategies, and verify AI-built software.
Quantitative alpha factor research. Systematic signal discovery, backtesting, and portfolio construction.
EXPLORE →Follow one BTC/USD strategy from market data and research through validation, Alpaca paper execution, scheduling, and monitoring.
EXPLORE FORGE LEARN →Premium trading infrastructure automation. AWS cloud deployment, monitoring, and operations.
DEPLOY →"Working with Brian on a fintech application was a pleasure. Not only is Brian very knowledgeable as a Chartered Financial Analyst, but he was a fantastic resource when it came down to programming the application itself. His Python skills are top notch, and he was able to introduce me to developer tools and practices that I still use today."
"I had the pleasure of working with Brian on our internal fintech application overhaul, where he demonstrated exceptional skills in data analytics and workflow automation. My project requirements were complex and a little fluid. However, his clear communication and proactive approach made collaboration seamless, resulting in a dramatic increase in my trading system's performance."
Five explanations, five tests. The settlement is public, the model lost to the book, our best feature was reading the future, there is no speed race, and the crowd test could not tell the wallet apart. Part 2 of the 8% wallet series.
READ MORE →
One Polymarket account won 398 of 4,707 bets and finished up 9,128. Four tests failed to explain it, and the last one pointed at volatility rather than direction.
READ MORE →
Our walkforward said FanDuel +4% and DraftKings +7%. Then the data behind it was destroyed, and what we rebuilt was smaller, stranger and more useful.
READ MORE →
As intelligence becomes abundant, judgment becomes more scarce.
READ MORE →
Slow backtests, blown memory, and the coding habits I wish I’d caught sooner.
READ MORE →
A LightGBM model made money on NFL totals at both FanDuel and DraftKings. The same-side agreement filter looked stronger, but its historical edge is a lead for one locked 2026 test, not a betting strategy.
READ MORE →Get research updates, trading insights, and Python tutorials delivered to your inbox.
By clicking "Subscribe," you agree to our Terms of Use and acknowledge our Privacy Policy. You can unsubscribe at any time.
No spam. Unsubscribe anytime.