Automated Trading Championship 2007: Interview with Boris Vilenski (bablokos)
Really successful automated trading experts are impossible in nature.
Why? The answer is obvious, because you can not predict what is impossible to predict. Financial market is like any other socioeconomic system is a COMPLEX SYSTEM that is selforganizing, chaotic, clustered in its nature. It is impossible to derive profitable trading system what is less complex than system it is trying to predict. In order to predict the activity of complex system the trading system MUST be as complex as financial market itself. So that’s why it is impossible.
But people question me: Why there are so many examples of successful traders, does it mean that prediction is possible?
Not exactly. There works so called population learning. Learning on the level of population [thru trials and errors] produces the sample of successful traders and also does a waste of unsuccessful one. Who succeed advertise themselves, who failed shout up. So there is such misleading statistics: many of successes but few of failures.
One of the ideas is to use population learning in trading systems, i.e. exploit genetic algorithms to breed successful traders (AI) thru principle of natural selection. Because lifespan of any trading system is always limited the system must adapt or evolve by constantly producing new trading strategies and trying to adapt to constantly changing market environment.
Only in this case the system will be as complex as market itself.
Why? The answer is obvious, because you can not predict what is impossible to predict. Financial market is like any other socioeconomic system is a COMPLEX SYSTEM that is selforganizing, chaotic, clustered in its nature. It is impossible to derive profitable trading system what is less complex than system it is trying to predict. In order to predict the activity of complex system the trading system MUST be as complex as financial market itself. So that’s why it is impossible.
But people question me: Why there are so many examples of successful traders, does it mean that prediction is possible?
Not exactly. There works so called population learning. Learning on the level of population [thru trials and errors] produces the sample of successful traders and also does a waste of unsuccessful one. Who succeed advertise themselves, who failed shout up. So there is such misleading statistics: many of successes but few of failures.
One of the ideas is to use population learning in trading systems, i.e. exploit genetic algorithms to breed successful traders (AI) thru principle of natural selection. Because lifespan of any trading system is always limited the system must adapt or evolve by constantly producing new trading strategies and trying to adapt to constantly changing market environment.
Only in this case the system will be as complex as market itself.
adamlevin:
Really successful automated trading experts are impossible in nature.
Why? The answer is obvious, because you can not predict what is impossible to predict. Financial market is like any other socioeconomic system is a COMPLEX SYSTEM that is selforganizing, chaotic, clustered in its nature. It is impossible to derive profitable trading system what is less complex than system it is trying to predict. In order to predict the activity of complex system the trading system MUST be as complex as financial market itself. So that’s why it is impossible.
Really successful automated trading experts are impossible in nature.
Why? The answer is obvious, because you can not predict what is impossible to predict. Financial market is like any other socioeconomic system is a COMPLEX SYSTEM that is selforganizing, chaotic, clustered in its nature. It is impossible to derive profitable trading system what is less complex than system it is trying to predict. In order to predict the activity of complex system the trading system MUST be as complex as financial market itself. So that’s why it is impossible.
Hmm. If one's looking for fully autonomous (always) profitable trading system that runs almost infinitely, then I agree that the system probably will be as complex as the market itself.
But if one's only looking for fully autonomous system that runs at a finite time (like this championship) or runs at a longer time but not fully autonomous (eg. regularly supervised by the owner), then it is possible to build a profitable and not so complex trading system.
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
On the website of the Automated Trading Championship 2007, an Interview with Boris Vilenski (bablokos) has been published. The Participant from Israel decided to write an automated trading system based on his professional experience, though it is far from trading. Boris thinks that "for being successful, one should try to lead one's own way and search new solutions". And he does well.
The interview was published on the website of Automated Trading Championship 2007 in the News section.
The Automated Trading Championship 2007 is organized by MetaQuotes Software Corp. and co-sponsored by ODL Securities Limited, Alpari (UK) Limited, FXDD and the popular TRADERS` magazine.