Feature-engineering

This chapter explores the use of entropy as a feature for machine learning in finance.

This chapter explores how to derive predictive features from market microstructure data (like FIX messages).

This chapter tackles the problem of optimal clustering, which is a form of unsupervised learning.

This chapter argues that Pearson’s correlation is a limited measure of codependence because it is not a true metric, it only captures linear relationships, and it is sensitive to outliers.

This chapter argues that backtesting is not a research tool; it is a validation step prone to overfitting.

This chapter discusses methods for detecting structural breaks, which are transitions from one market regime to another (e.g., from mean-reversion to momentum).