I have recently read an interesting article in Futures Magazine about the existence (or lack thereof) of mean reversion in stocks. Under the authors' apparent conclusion that there is a significant degree of autocorrelation in the SPX with a one-day lookback period, they suggest a simple trading system where one would buy at close if close<open and sell at close if close>open.

Further looking into the mean reversion assumption, I tested (with optimization - sorry) the following system on SPY from 3/12/1997 to 5/8/2009, including some long-term trend filter:

LE: ref(c<ref(O,-8) and l>mov(c,282,e),-1)

LX: ref(c>ref(O,-1) or l<mov(c,282,e),-1)

SE: ref(c>ref(O,-1) and h<mov(c,282,e),-1)

SX: ref(c<ref(O,-8) or l>mov(c,282,e),-1)

With the following parameters:

Interest 0%

Margin 3%

100% available equity

Position Limit 1

Long Initial 100%

Long Maintenance 0%

Short Initial 200%

Short Maintenance 101%

Commissions $10

Realistic Market Price No

Delay to Open 0

All trades at Close

The results stats look good and the equity curve almost improbably good. Would anybody care to post comments on this system? Is it realistic from a practical point of view?

Many thanks.

ZigZag

tks for your reply johnl

As far as I understand, REF may be used that way. Would be curious to see your suggested code.

I am wondering if anybody bothered to run the system on daily SPY and if so, what are his/her thoughts?

More generally, does anybody have a system that attempts to exploit the existence (or lack thereof) of mean reversion in the stock market? Or any ideas?

This theme is very much in vogue given the demise of the mean reversion models widely used by hedge funds going into the Great Bust of 2008.