As I have worked more on the 101 Alphas project, it has become clear to me that there is a need for a toolset to evaluate Pipeline factors in the research environment.
When implementing a factor in a trading algorithm, the complexity and wide range of parameters involved with basket selection and trading logic hinder our ability to evaluate the value factor's alpha signal in isolation. Before we proceed to the implementation of an algorithm, we want to know if the factor has any predictive value.
In this analysis, we'll measure a factor's predictive value using the Spearman rank correlation between the factor value and various N day forward price movement windows over a large universe of stocks. This correlation is called the Information Coefficient (IC).
This tear sheet takes a pipeline factor and attempts to answer the following questions, in order:
- What is the sector-neutral rolling mean IC for our different forward price windows?
- What are the mean returns for each factor decile?
- How much are the contents of the top and bottom quintile changing each day?
- What is the autocorrelation in sector-wise factor rankings?
- What is IC decay (difference in IC for different forward price windows) for each sector?
- What is the IC decay for each sector over time?
- What are the factor quintile returns for each sector?
Please feel free clone and share your feedback below. How do your favorite factors look? Are there any more plots or figures you'd want to see?
For more information on Spearman Rank correlation, check out this notebook from the Quantopian lecture series.