by Dan Philps, Oleksandr Galkin, Ram Gopal, Szymon Kubiak, Tillman Weyde
Continue on SelfMadeQuant
Suggested foundations for portfolio construction and financial machine learning. Specialist prerequisites vary by paper.
Understand the covariance structure of portfolio risk.
Read objectives, constraints and optimality conditions.
Preserve time order and avoid future information in training.
Establish an interpretable baseline before a flexible model.
Construct allocations and examine sensitivity to estimated inputs.
Turn mathematical weights into feasible portfolio decisions.
Account for dependence and overlapping observations.
Connect diversification, common risk factors, investor views, and the properties of a risk measure.
Choose a reproducible strategy, specify the trading rule, and test what remains after costs and estimation uncertainty.