Hands-On Machine Learning for Algorithmic Trading

Built-in Quantopian factors

The accompanying notebook factor_library.ipynb contains numerous example factors that are either provided by the Quantopian platform or computed from data sources available using the research API from a Jupyter Notebook.

There are built-in factors that can be used, in combination with quantitative Python libraries, in particular numpy and pandas, to derive more complex factors from a broad range of relevant data sources such as US Equity prices, Morningstar fundamentals, and investor sentiment.

For instance, the price-to-sales ratio, the inverse of the sales yield introduce preceding, is available as part of the Morningstar fundamentals dataset. It can be used as part of a pipeline that is further described as ...