Ed Mamula.com

# closed winning trades : 5

# closed losing trades : 2

Net monthly return on risk capital : (-8.5 %)

Once again, I’m sure I know why hedge funds have lockup periods and report results on a monthly basis.  With leverage, it’s always an adventure!  I’m now 10 weeks deep in a drawdown, and this one is peculiar…it has not been very deep, and the percentage of winning trades looks normal, HOWEVER, the size of the winning trades, particularly in October, has been quite small.  I actually had one loss, and a streak of five winners in a row that put the system up only about 5% for the month.  One quick loss this AM put me back in the red for the month.  One notable thing is that Cable Glider shows a combined net loss on all trades entered on Friday after 8AM New York time for 2007.  Indeed, as US stock market volatility has picked up over the past few months, it’s often been rough sledding for the Cable Glider in the US session.

Of course, this net negative performance did not happen in 2006, so it leaves me struggling with the idea of just how long the lookback window should be when I’m testing a system that runs on 30 minute bars.  So far, the things I’ve read on the subject are not satisfying; they appear to be rules of thumb much like the stock / bond asset allocation formula that says “subtract your age from 100 and put that percentage of your money in stocks”…just lovely, but certainly not rigorous.

Once again, I have to say that Cable Glider is still my best system by far, and I can see no reason to believe that it is “broken”, so as usual, I will follow the system and see what next week brings.

When optimizing a trading system, the first question we must answer is what it is that we are trying to maximize.  We can call that our fitness function.  I’m quite a newbie in this area, so the fitness function that I use is not presented as a recommendation, but rather a simple recording of where my thoughts on the process currently reside.

First of all, I do not want my fitness function to be dominated by recent results, so I do not “reinvest” my profits when testing a system;  I presume that I have a fixed starting equity for every trade and risk a percentage of that equity. 

Secondly, since the Cable Glider is quite profitable, the equity curve quickly looks like an exponential function, so I use logarithms whenever possible in order to normalize various pieces of the fitness function that would otherwise be on entirely different scales.  This is  an attempt at finding a fitness function that is not dominated by a single sub-component.

Thirdly, I think what I like and what I don’t like.  I like profit.  I dislike losses.  I like a high winning percentage.  I like the average win size to be greater than the average loss size.  I dislike drawdowns.  I want to be certain that I have a quantifiable edge that suggests my trading results are better than playing a coin flipping game.

I will post the specific function that I’m using in my next post.  In preparation, please read Ed Seykota’s page on risk management.  My fitness function incorporates the Kelly criterion described on that page.