Pattern recognition / Trading without indicators

The issue would be something like this ...

system A has return of 20% and drawdown of 20%
system B has return of 10% and drawdown of 20%

Is is worth trading both systems? What is the main metric (or metrics) for evaluating the combined system?

Let's say system A+B has return of 20% and drawdown of 10%, then I would argue you should trade them together. But what if A Sharpe = 1.2 and B Sharpe = 1.0, and A+B Sharpe (no music jokes please) = 0.9, is the combined system better?

Maybe you also need to look at Sortino for the combined, especially if both systems have low-ish win rates.

This may all sound a bit academic, but the more I think about it, the more I think this is a sound approach to portfolio management of systems.


This may all sound a bit academic, but the more I think about it, the more I think this is a sound approach to portfolio management of systems
(y)

I completely agree.

Maybe you also need to look at Sortino for the combined, especially if both systems have low-ish win rates.

Again i gree!

Since the drawdowns of the systems are both greater than, or equal to the expected return then this initially might make you think that it was never possibility. Esspecially if you are only using a sharpe ratio instead of a sortino....However!

When initially looking at the numbers and checking the feasability, you would have to initially deduce the drawdown of both systems by summing them togeher...20%+20%=40%

but this may not neccesseraly be the case......It all depends how the numbers fall

If the systems have low win rates(40%or less) then the sortino ratio would give you the true corellation between both systems. Much more accurately than the sharpe would IMO.
 
Ok, I've done some preliminary research into this and thus far the conclusion is something along the lines of (wait for it .. )

- for two highly correlated (>+40%) systems, the Sortino of the combined system is lower than either of the two individuals, whereas for two less correlated (<+25%) systems, combined Sortino could well be higher than that of either of two individuals.

So ............. if you're going to trade two systems, or two approaches, I think first and foremost you'd like them to both have positive expectancy. Then, beyond that, a low-ish correlation such that Sortino for the combined is larger.
 
Ok, I've done some preliminary research into this and thus far the conclusion is something along the lines of (wait for it .. )

- for two highly correlated (>+40%) systems, the Sortino of the combined system is lower than either of the two individuals, whereas for two less correlated (<+25%) systems, combined Sortino could well be higher than that of either of two individuals.

So ............. if you're going to trade two systems, or two approaches, I think first and foremost you'd like them to both have positive expectancy. Then, beyond that, a low-ish correlation such that Sortino for the combined is larger.

forgot about this....you may have seen it already but i think its good....And one of the trading greats is an advocate of this....Seykota!

http://www.seykota.com/tribe/risk/index.htm
 
Nice article, I'd certainly concur with the sticking to the system part. I keep detailed records of all my trades, along with those signals I didn't take.. skipping signals cost me a lot of money last year, my goal is not to do that again this year (within reason).
 
Nice article, I'd certainly concur with the sticking to the system part. I keep detailed records of all my trades, along with those signals I didn't take.. skipping signals cost me a lot of money last year, my goal is not to do that again this year (within reason).

Is it not contradictory to skip signals ''(within reason)'' ?
 
Yes, I suppose it is, but really what I was referring to was missing signals due to either being unable to access the internet whilst away, or perhaps an emergency or illness preventing trading.

Furthermore, there are occasions when one might want to modify the system - this would then lead to signals from the previous system being skipped and so on.

In other words, I don't want to make "taking signals" out to be a matter of life and death ... !
 
Yes, I suppose it is, but really what I was referring to was missing signals due to either being unable to access the internet whilst away, or perhaps an emergency or illness preventing trading.

Furthermore, there are occasions when one might want to modify the system - this would then lead to signals from the previous system being skipped and so on.

In other words, I don't want to make "taking signals" out to be a matter of life and death ... !

Hey MeanReversion,

Watch the link below and watch all the parts......EXCELLENT ADVICE! (y)(y)

 
Top