Machine Learning for Markets

Where ML genuinely helps, where it misleads, and how to use it without fooling yourself.

• ML in Markets: Hype vs RealityWhat machine learning can and cannot do in noisy, adversarial, non-stationary markets.8 min
• Features: Garbage In, Garbage OutThe model is only as good as what you feed it. Building features that carry real signal.7 min
• Train/Test Splits & LeakageIn time series, a careless split leaks the future into the past. The pitfall that fakes great models.7 min
• Overfitting in MLFlexible models memorise noise even faster than humans. Regularisation and humility.7 min
• Explainability & TrustA black box you cannot question is a black box you cannot trust with money. Opening it up.6 min