Use computerized evolution to create trading system?

[jack hershey]

Quote from futurecurrents:

Oh yeah, I thought everyone knew that.

But let's not forget that market action can be analogous with the hydrological processes and interactions of an enclosed fluid body within parameters of shoreline wherein inputs of wind direction and strength interact to cause waves of action that then reverberate off shoreline and bottom. These waves do not disappear but continually interact on an exponentially decaying basis These waves can then, from within the chaos of interactions, superimpose themselves one upon another or cancel each other out. Thus from seeming chaos can there be synchronate activities resulting in peaks and troughs that the trade-wind sailor can use to hasten the journey. Undercurrents can often be deduced by their actions upon the visible waves. The peaks and troughs belie an inherent consistency within the chaos and by considering the trend of the inputs one can harness these forces to help progress one toward the anticipated course.

Have you been on a ship going from Cape Hook to the tip of Antarctica or vice versa. You would sail through the "convergence". There are many more things at play on that route.

A person who looks at the processes the opposite way you mention, will make more forward progress than looking at it the way you did.

The wheat races long ago were a tribute to those who knew what they were doing.

Applying science to the markets is not very difficult. My posts are intended to make very clear how it turns out when that is done in one of the many ways that it is possible.

Elsewhere there is a post where a person reviews what he thinks the majority do. He thinks they can guide him.

 

[caementarius]

Quote from futurecurrents:

Oh yeah, I thought everyone knew that.

But let's not forget that market action can be analogous with the hydrological processes and interactions of an enclosed fluid body within parameters of shoreline wherein inputs of wind direction and strength interact to cause waves of action that then reverberate off shoreline and bottom. These waves do not disappear but continually interact on an exponentially decaying basis These waves can then, from within the chaos of interactions, superimpose themselves one upon another or cancel each other out. Thus from seeming chaos can there be synchronate activities resulting in peaks and troughs that the trade-wind sailor can use to hasten the journey. Undercurrents can often be deduced by their actions upon the visible waves. The peaks and troughs belie an inherent consistency within the chaos and by considering the trend of the inputs one can harness these forces to help progress one toward the anticipated course.

http://www.youtube.com/watch?v=RXJKdh1KZ0w

 

[kut2k2]

Quote from Random.Capital:

Evolution itself is a curve-fitting process.

Strongly disagree. There is no grand master plan (i.e., "curve") being fitted by evolution. We'd be descended from velociraptors rather than from monkeys if not for the black swan of a big asteroid slamming into this planet. Shit happens, especially random shit, and evolution adapts to it.

 

[ElectricSavant]

out of sample....

Quote from ronblack:

They have no idea of what they are talking about on that blog. One pig-ignorant guy is attacking another pig-ignorant guy.

Trading systems created by evolutiononary processes are basically curve-fitting systems unless a number of conditions are met, which I am not going to discuss here because they are the basis for coming up with an edge.

 

[LeeD]

Quote from kickout:

I'm fairly familar with RapidMiner and VERY familar with R....I'm always curious how people trade with these tools..Do you have a custom c++ code that calls these programs (if possible) to generate a signal? Thats the only part i cant quite solve...

In many practical cases it's discovering a trading strategy and choosing parameters (if any) that is a difficult task.

Once this has been accomplished, a lot of strategies are computationally simple and can be coded with a moderate effort directly into the chosen charting/autotrading platform (or even Excel).

Those few strategues that actually have to run complex computations in real time can use a 3rd party library or indeed call directly into R.

 

[LeeD]

Quote from ElectricSavant:

out of sample....

Out-of-sample testing is an invaluable tool but it doesn't (and can't) eliminate curve-fitting entirely. As soon as among backtested strategies you start picking those with satisfactory out-of-sample performance, you introduce data-mining bias and end up with the same spectrum of problems you tried to eliminate by introducing forward-testing.

 

[goodgoing]

Quote from LeeD:

Out-of-sample testing is an invaluable tool but it doesn't (and can't) eliminate curve-fitting entirely. As soon as among backtested strategies you start picking those with satisfactory out-of-sample performance, you introduce data-mining bias and end up with the same spectrum of problems you tried to eliminate by introducing forward-testing.

It is not the same spectrum of problems. Data mining bias can be a good bias. It can work for you rather than against you. Do you actually think that data mining bias is always bad?

 

[LeeD]

Quote from goodgoing:

It is not the same spectrum of problems. Data mining bias can be a good bias. It can work for you rather than against you. Do you actually think that data mining bias is always bad?

The point of my post was simply that if not used very carefully forward-testing introduces very much similar problems to those it is used to solve. I.e. selection bias... By choosing trading sytems that perform well on a forward test we indirectly choose systems that are fitted to the forward-test period.

I haven't seen a practical case where data-mined systems would consistently perform better than on the in-sample tests. If your perception is I am missing this big part of the data-mining goodness, please enlighten me.

 

[goodgoing]

Quote from LeeD:

The point of my post was simply that if not used very carefully forward-testing introduces very much similar problems to those it is used to solve. I.e. selection bias... By choosing trading sytems that perform well on a forward test we indirectly choose systems that are fitted to the forward-test period.

I haven't seen a practical case where data-mined systems would consistently perform better than on the in-sample tests. If your perception is I am missing this big part of the data-mining goodness, please enlighten me.

I missed your reply and I thought it is too important to ignore. In principle I agree with you. I have been able to get data-mined system that are as good in the OOS as they were in the IS, not better though. See also this post:

http://www.elitetrader.com/vb/showthread.php?s=&postid=3546776#post3546776

If I can get data-mined systems with a profit factor of at least 50% of that calculated for the IS, then I am satisfied because in most cases it simply means that those favorable condtions in the IS that gave a boost to the profit factor were not present in the OOS.