Hands-On Machine Learning for Algorithmic Trading

Universe creation and time horizon

We will use equity data for the years 2014 and 2015 from a custom Q100US universe that uses built-in filters, factors, and classifiers to select the 100 stocks with the highest average dollar volume of the last 200 trading days filtered by additional default criteria (see Quantopian docs linked on GitHub for detail). The universe dynamically updates based on the filter criteria so that, while there are 100 stocks at any given point, there may be more than 100 distinct equities in the sample:

def Q100US():    return filters.make_us_equity_universe(        target_size=100,        rankby=factors.AverageDollarVolume(window_length=200),        mask=filters.default_us_equity_universe_mask(),        groupby=classifiers.fundamentals.Sector() ...