Where AI Can Help in a Trading Workflow: Three Short Examples
Three short examples of where AI helps in a trading workflow: faster strategy coding, scoring text with a language model, and reproducing finance papers.

Three short examples of where AI helps in a trading workflow: faster strategy coding, scoring text with a language model, and reproducing finance papers.

Book review of Hands-on Financial Trading with Python, 2nd Edition by Cordell Tanny: a process book on backtest validation, lookahead bias and deployment.

Live 3-hour online masterclass on Nov 14, 2026 with Chris Tubby: using AI for market analysis, indicators and trading bots, with risk controls.

A deterministic oscillator and a random walk can share almost the same standard deviation. Why sample volatility cannot reveal the process behind a price series.

Does a trading strategy’s performance metric change shape in stressed markets? Convexity and concavity show what the unconditional average hides.

CVaR plays three roles in portfolio work: a risk measure, an input to performance ratios, and a portfolio-construction objective. Part 1 of 3.

Delta replication of the S&P 500 with options in 2024: how the replication error differs for fixed 20% volatility, 21-day realized volatility and the VIX.

Mean squared error bundles three separate checks: bias, direction and volatility. See the MSE decomposition and why MSE reaches zero only when all three hold.

Review of Building AI Agents for Finance by Dupouy and El Mofatiche: production-grade multi-agent systems, framework comparison, and compliance-ready evaluation.

Research article on topological anomalies and return predictability in the S&P 500 accepted for publication in Bank i Kredyt. Preprint on arXiv and SSRN.