by J. B. Heaton, J. H. Witte, N. G. Polson
Continue on SelfMadeQuant
Suggested foundations for financial machine learning. Specialist prerequisites vary by paper.
Preserve time order and avoid future information in training.
Establish an interpretable baseline before a flexible model.
Account for dependence and overlapping observations.
Examine which information contributes to predictions.
Choose a reproducible strategy, specify the trading rule, and test what remains after costs and estimation uncertainty.