Intraday Patterns In Stock Price Movements - AlgoJi

The aggregate trading stimulants/activity of large players create short-term patterns in stock price behavior, suggests a study entitled “Are You Trading Predictably?”. The Authors calculate returns over 13 half-hour intervals each day using intraday bid and ask prices for 4,494 U.S. stocks over the period of January 2001 through December 2009.

Research - Intraday Patterns in Stock Price Movements

For a simple univariate cross-sectional regression of the form r(i,t) = α(k,t) + γ(k,t)r(i,t-k) + u(i,t), where variable r(i,t) is the return of stock iduring interval t and the variable r(i,t-k) is the return of stock i in interval (t–k), the above graph plots the time-series averages of γ(k,t) (in percent).

  1. Stocks which outperform the market in a given half-hour interval tend to exhibit rapidly decaying underperformance over the next several hours, followed by periodic outperformance in the same half-hour interval on subsequent days.
  2. This effect is notably stronger for the first and last half-hours of the trading day, but exists for all half-hour intervals.
  3. The effect is consistent across years in the sample period, except for a possible reduction in magnitude during 2009.
  4. Percentage changes in trading volume exhibit a similar pattern, but do not explain the return pattern.
  5. The magnitude of the pattern is sizeable relative to institutional commissions and effective spreads, so randomizing or (better) shifting trade timing to exploit the pattern could substantially reduce friction for frequent, low-cost traders.

Free Webinar Series on Algorithmic Trading

29th May | From Concept to Automation – 9 Trading Strategies
30th May | Algorithmic Trading using Machine Learning in Python
31st May | Kickstart Guide to Algorithmic Trading
1st June | Algorithmic Trading Using Amibroker and MTv3