Join waitlist
The books... not free though
10 Strategier Som Slår BörsenSvenska10 Strategier Som Slår Börsen10 Strategies That Beat the MarketEnglish10 Strategies That Beat the MarketProRealTime Coding Made SimpleEnglishProRealTime Coding Made Simple
600+StatisticsMarket statistics and edges1,327StrategiesBacktested strategy library18Research papersThe study behind the algos301DocsProBuilder coding reference27Algo development programCourses and lessons24Everything here feeds the 24 algosSee the algos

Stats › Intraday and market microstructure › Retail order flow

Retail order flow predicted returns, and then the tradeable part of it stopped

One week ahead|t 15.14 then 7.952010 to 2015: 0.00092016 to 2021: 0.00060.0006Two weeks|t 9.48 then 3.462010 to 2015: 0.00062016 to 2021: 0.00030.0003Four weeks|t 5.64 then 2.022010 to 2015: 0.00032016 to 2021: 0.00020.0002Six weeks|t 4.53 then 2.102010 to 2015: 0.00032016 to 2021: 0.00020.0002Eight weeks|t 3.96 then 1.792010 to 2015: 0.00022016 to 2021: 0.00010.00012010 to 20152016 to 2021

Fama-MacBeth coefficients on retail order imbalance in dollar volume, predicting returns k weeks ahead. The point estimates fall by a third to a half and the t statistics fall by more. The figures come from a replication that reproduces the original tables with high precision; the original paper itself was not opened.

Retail order imbalance predicted next week's returns with a t statistic of 15.14 over 2010 to 2015. Over 2016 to 2021 the coefficient falls by a third and the long short strategy's alpha is no longer significant at any horizon across all stocks.

0.0009, t = 15.14Next-week coefficient on retail order imbalance, 2010 to 2015
0.0006, t = 7.95The same over 2016 to 2021
0.437% then 0.143%Small-cap one-week long short alpha, the two periods
28%Share of real retail trades the standard algorithm mis-signs

Members only

The rest of this page is for members

Below this point there are 5 sections and 3 named sources, roughly 600 words of it. Every figure carries the source it came from and the date the data is from.

You can keep browsing every statistic in the library for free. The intro and the summary are always open.