In an idealized world, categories of risk factors should be independent of each other (orthogonal), yield positive risk premia, and form a complete set that spans all dimensions of risk and explains the systematic risks for assets in a given class. In practice, these requirements will hold only approximately. We will address how to derive synthetic, data-driven risk factors using unsupervised learning, in particular principal and independent component analysis in Chapter 12, Unsupervised Learning.

We will review the key categories for factors derived from market, fundamental, and alternative data, and typical metrics used to capture them. We will also demonstrate how to implement these factors for algorithms tested on the Quantopian platform using built-in factors, custom computations using numpy and pandas, or the talib library for technical analysis.