Tuesday, January 1, 2013

Intraday mean reversion

In my previous post I came to a conclusion that close-to-close pairs trading is not as profitable today as it used to be before 2010. A reader pointed out that it could be that mean-reverting nature of spreads just shifted towards shorter timescales. I happen to share the same idea, so I decided to test this hypothesis.

This time only one pair is tested: 100$ SPY vs -80$ IWM. Backtest is performed on 30-second bar data from 11.2011 to 12.2012.
The rules are simple and similar to strategy I tested in the last post:
if bar return of the pair exceeds  1 on z-score, trade the next bar.
The result looks very pretty:

I would consider this to be enough proof that there is still plenty of mean-reversion on 30-second scale.
If you think that this chart is too good to be true, that is unfortunately indeed the case. No transaction costs or bid-ask spread were taken into account. In fact, I would doubt that there would be any profit left after subtracting all trading costs.
Still, this kind of charts is the carrot dangling in front of my nose, keeping me going...


  1. it would be interesting to see the same test done on hourly data - this could be resistant to transaction costs as well, Jozef

  2. 30 sec - this resolution is to small, as you delay with Bid-ASk bounce, nonsynch data and all the other micromarket noise. A more resonable way would be to from daily to hourly in a first step

    Keep the carrot dangling.........

  3. According to Epps Effect, it is knowned that pairs have low correlation if the timeframe become short(small). I think your result is based on some kind of chaotic environment as using very short timeframe chart which has so many mean reversion. Actually I have the quiet good result that make profit with including trading cost in foreign exchange market. Test was conducted with 1 hour data and strategy is based on market neutral spread.

  4. Hello Hyojun Moon,

    Can tell me a example of market neutral spread in foreign exchange market please ?!


    1. It is quiet hard to explain with text. Maybe you can search for statistical arbitrage based on spread mean reversion dissertation alternatively

    2. you can make market neutral spread by selecting pairs like gbpusd and eurusd. They are highly correlated(still liitle bit cointegrated) in fundamental point or statistical point. it may be good to choose not very high correlated pairs like index etf-index but highly correlated to trade safely and cointegrated,which means pairs are vibrating between linear trend line. you may need forex margin trading as it needs leverage to make real profit.