by Kei Nakagawa, Kiyoshi Izumi, Masaya Abe, Tomoki Ito
Continue on SelfMadeQuant
Suggested foundations for asset pricing and factor research and financial machine learning. Specialist prerequisites vary by paper.
Establish an interpretable baseline before a flexible model.
Work with returns and recognise their empirical limitations.
Preserve time order and avoid future information in training.
Connect factor definitions to portfolio construction.
Distinguish exposure estimation from tests of expected returns.
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.