AlphaScreener Momentum is based on the work of Da, Gurun, Warachka, et al, as reported in this paper.
This approach attempts to take advantage of the fact that investors tend to underreact to small amounts of information that arrives continuously. It focuses on continuous and frequent gradual changes in price, which attracts less attention as opposed to infrequent dramatic changes (which could be caused by some news or other external factors).
Figure 1 above illustrates the difference between continuous vs. dramatic price change. Even though the end results are the same (in terms of percentage price change), the paths to get there are different.
The authors in the original paper called this the “frog-in-the-pan hypothesis” (FIP), whereby a “series of frequent gradual changes attracts less attention than infrequent dramatic changes. Investors, therefore, underreact to continuous information”. They found that this type of momentum persists longer.
Now that you understand the theory. Let’s talk about the math. On a daily basis, AlphaScreener looks at all active stocks and calculates the information discreteness score (or ID), as follows:
The AlphaScreener system sorts all stocks based on the 6 months return and the ID score.
Note that this is one approach to define momentum. There are other methods to measure and define momentum. For more information on the topic, you can read the original paper from 1993 by Jegadeesh and Titman or AQR’s paper explaining the persistence of the momentum factor.