|
PureBytes Links
Trading Reference Links
|
At 4:57 AM -0400 10/20/98, Orphelin@xxxxxxx wrote:
>No need of a discretionary method to filter out this. It's programmable,
>but with some AI software: Either a data mining one ( you will need
>thousands of signifiant cases), or another that I know better.
>The problem is vey simple to post: You want a sell signal on a turn down
>and a crossover ofthe K% D%. You know by experience that the level at
>which the crossover will be valuable is not the same according to external
>market conditions.
>So, you need to find out what could be the " driving" indicator ( the one
>that moves the K% D% level of decision). Say for example that it's an ADX
>based relationship (makes sense).
>You will have to find out a bunch of rules to have valid signals with your
>KD crossover and the ADX. Suppose that you could do this by hand, it will
>take some hours and a great deal of trial and error.
>Suppose now that there are two driving indicators: say ADX and volatility
>(makes sense too, and both are carrying different information). Will you
>spend a week or two to build the system that becomes quite complicated,
>probably hundreds of rules. I guess you will not...
>Now, something shoud be taken in account: the slope of the trend. We are
>candidate now to write a thousand of rules to correctly interpret the K%
>D% crossover that is driven by 3 external indicators.
>Does it means that it's impossible to write the rules ? No. It's only
>beyond the scope of your brain and of any human brain. It's easy to a fast
>silicon chip with some software.
>Draw your conclusion by yourself...
This makes some sense to me but I wonder if it is the most productive approach.
In the example you cite, stochastics (K% D%), ADX, volatility, and the
"slope of the trend" are all indicators based solely upon price. So past
values of price are the only information this system is using. (I
understand that we could also use other data such as volume or interest
rates but that is not relevant to my argument.)
Assume that your AI system could "learn" some combination of rules that
will interpret all of the above four "indicators" based upon all of the
past price data available to train it. Clearly, as you state, there would
be thousands of rules.
So now we start with price, calculate four different derived indicators,
and learn thousands of rules to combine the values of the four indicators
into trading signals. I will even assume your system can do this - quite an
achievement.
But, it is not at all clear to me is that this combination would do a
better job than a system that derives trading signals directly from price.
In addition, I would be very worried that the thousands of rules might have
embedded in them, some hidden "resonance effect" that might get "excited"
by some unexpected combination of prices that the system has never seen
before. This could cause it to behave erratically. We are told that the
crash of the LTCM hedge fund was due to a combination of circumstances that
the model was not programmed to expect. (As that expression goes, "Sh--
happens".)
Then, what if I am using this system and it begins to act strangely. What
do I do? There is no way I can understand what is really going on with all
of those rules. Do I just stop using it? When do I stop using it? When do I
start using it again?
With my system based directly upon price data. It is easy to understand
what is really going on since the relationships are logical and pretty
simple. If it starts behaving strangely, I can usually understand why. I
can usually create a test case that will simulate the strange behavior. I
can then even add more code to cover that case in the future by
INCREMENTALLY adding code to improve what already works WITHOUT CHANGING
what already works. This is a key point. Most of human experience, such as
the law, keeps what works and INCREMENTALLY fixes what doesn't work.
With your system, as I understand it, if I want to train it for new
conditions, I have to add the new price data and retrain it. The result is
some new, different combination of thousands of rules and this new system
will work differently than the previous system. Any experience I have
developed with the old system of rules is gone.
I will acknowledge that your system can possibly find some hidden
relationship that I didn't recognize and can possibly get better results on
the kind of price data it is trained on. But I question if that advantage
is worth risking money on a computer model that you cannot understand.
I admit that I have no experience with your system so could misunderstand
how it works.
Bob Fulks
|