Optimization of a trading system with avoidance of curve fitting.

[DT-waw]

Quote from intradaybill:

Selection bias may turn out to be a good and even necessary process for trading system development.
.

selection may also turn out to be bad.
exactly like with parameters- may turn out to be good or bad in the future.
correct- everything is selection, choice. you select the markets, time frames, general type of strategy, parameters.

If your returns were great by choosing Gold as the only market to trade in the last 2 years, its just curve fitting to this particular market...

semantics.
the only thing that matters with trading systems is:
how to adapt to ever changing market conditions: trends, volatility, bid-ask spreads, volume.
forecasts, neural networks or tech. indicators: it totally does not matter.
the question is: how a particular method responds to changing markets?
how much it can potentially lose when market is noisy, random or going strongly in one direction?

 

[Eight]

Quote from DT-waw:

no matter what rules are used, i think everyone would like to see rising equity curve of the system.

if the equity curve is rising it automatically means, the system was fitted to the historical chart. otherwise it would not make any profits.

a system with 100% random entries (not curve fitted) will produce zero profit over the long run.

99.9% of traders cannot grasp what i've wrote above!

You seem to assume that there is no system that escapes randomness...

 

[DT-waw]

Quote from Eight:

You seem to assume that there is no system that escapes randomness...

the opposite.
systems based on variety of methods (incl all tech. indicators) are capable of making huge returns on markets. reason: markets overshoot very much, driven by crazy emotional "investors".

 

[DT-waw]

Quote from intradaybill:



I suggest you visit any on the sites that offer historical fund data and take a look at mechanical trading programs that have produced consistent high returns for many years.

thanks, i'm aware of 100s of CTAs performance.
most of them ( except giants like Winton, QIM) totally don't care about risk. most don't have the slightest clue how to reach 30% p.a. returns. , because they focus and have credentials solely within marketing and sales.

anyway, markets will change and will trend. those who will adapt will survive

 

[intradaybill]

Quote from Eight:

You seem to assume that there is no system that escapes randomness...

That is exactly what he (DT-waw) assumes but the funny thing is that he doesn't understand his own assumptions and later comes to invalidate them. He is also using them selectively.