Bias Algorithms? How Ironic!

Bias Algorithms? How Ironic!

February 12, 2014 Research Insights
Print Friendly
(Last Updated On: January 18, 2017)

Human bias in algorithmic trading


This paper documents a stark periodicity in intraday volume and in the number of trades. We find activity in both variables spikes by about 20% at regular intervals of 5 or 10 minutes throughout the trading day. We argue that this activity is the result of algorithmic trading influenced by human traders/programmers’ behavioral bias to transact on round time marks. An alternative explanation, that algorithms choose to concentrate their trades in time to take advantage of lower costs or to protect themselves from better informed traders, is not supported.

Data Sources:

Nanex, 2003 to 2006.

Alpha Highlight:

Trading takes place at specific time intervals. Why didn’t the programmer tell the algo to trade at random times?


Trading volume spikes every 5 or 10 minutes and returns to normal volumes 30 seconds later.


Strategy Summary:

  1. Paper finds that trading activity explodes on round time marks, such as every half hour.
    • Trading data (from Nanex) are quoted from 30 liquid U.S. stocks and 3 ETFs from April 17, 2003 to Oct 18, 2006, or a total of 882 trading days.
      • Figure 1 shows aggregate volume exhibits U-shaped pattern with sharp spikes in every 5 to 10 minutes.
      • Figure 2 shows percent changes in volume for each 30-second and spikes occur at highly regular intervals (30 minutes apart).
  2. Paper then tests two competing hypotheses to explain this increased activity.
    1. Hypothesis 1: Round Numbers Hypothesis
      • Theory is that humans have a tendency towards round numbers when faced with decisions.
      • Test: Paper regresses the volume and trade variables on various non-overlapping time dummies to examine whether clustering is progressively more intense as the markers on the time line becomes more and more round.
      • Time dummies correspond to round hour marks (10:00 AM), half-hour marks (10:30 AM), fifteen minutes marks (9:45 AM and 10:15 AM), ten minutes marks (9:40 AM and 10:10 AM), and 5 minutes marks (9:55 AM and 10:05 AM).
        • Table 2 shows average volume increases on the corresponding time marks, indicating that humans tend to prefer round numbers.
    2. Hypothesis 2: Rational Concentration Hypothesis
      • Theory is that liquidity traders tend to cluster trading to protect themselves from better informed rivals (insiders) and take advantage of increased liquidity and reduced transaction costs.
      • Test: Paper calculates 5 measures of transaction costs and 1 measure of price impact (see p11) and then, regresses each liquidity variable on various time dummies to check whether there is a significant improving in liquidity on the round time marks.
        • Table 3 shows that five measures of liquidity do not change in any significant way during the spikes (fails to support hypothesis 2).
    • Results: Inclined to attribute the clustering to the human preference for round numbers rather than to a rational optimizing activity of traders and their algorithms.

Strategy Commentary:

  • Documents the behavioral bias the people prefer to use round numbers when faced with a task in an uncertain environment.
    • Good summary of the literature with examples of humans’ bias towards round numbers (in financial economics, psychology, and marketing).
  • This paper makes sense!  When was the last time you scheduled a meeting at a time not ending in a 0 or 5?
    • Recommend meeting at 9:37 and see what reaction you get.

Wonder how many “algo hunters” are taking advantage of this already?

Note: This site provides NO information on our value investing ETFs or our momentum investing ETFs. Please refer to this site.

Join thousands of other readers and subscribe to our blog.

Please remember that past performance is not an indicator of future results. Please read our full disclosures. The views and opinions expressed herein are those of the author and do not necessarily reflect the views of Alpha Architect, its affiliates or its employees. This material has been provided to you solely for information and educational purposes and does not constitute an offer or solicitation of an offer or any advice or recommendation to purchase any securities or other financial instruments and may not be construed as such. The factual information set forth herein has been obtained or derived from sources believed by the author and Alpha Architect to be reliable but it is not necessarily all-inclusive and is not guaranteed as to its accuracy and is not to be regarded as a representation or warranty, express or implied, as to the information’s accuracy or completeness, nor should the attached information serve as the basis of any investment decision. No part of this material may be reproduced in any form, or referred to in any other publication, without express written permission from Alpha Architect.

Definitions of common statistics used in our analysis are available here (towards the bottom)

About the Author

Wesley R. Gray, Ph.D.

After serving as a Captain in the United States Marine Corps, Dr. Gray earned a PhD, and worked as a finance professor at Drexel University. Dr. Gray’s interest in bridging the research gap between academia and industry led him to found Alpha Architect, an asset management that delivers affordable active exposures for tax-sensitive investors. Dr. Gray has published four books and a number of academic articles. Wes is a regular contributor to multiple industry outlets, to include the following: Wall Street Journal, Forbes,, and the CFA Institute. Dr. Gray earned an MBA and a PhD in finance from the University of Chicago and graduated magna cum laude with a BS from The Wharton School of the University of Pennsylvania.