Machine learning in trading: theory, models, practice and algo-trading - page 2077
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
What candles 10-20-10 ?
you just compare with a logical condition? more/less true/false ?
that's it?
Do you just compare with a logical condition? more/less true/false?
that's it?
Yes, the pattern is built according to the conditions - this segment is longer (shorter) than the other one, etc.
Yes, the pattern is built according to the conditions - this segment is longer (shorter) than the other one, etc.
Don't you think it's too primitive?
don't you think it's too primitive?
No I don't, I'm sure it's primitive.
No it doesn't, I'm sure it's primitive.
)))
Look, it's easier, I also puzzled for years...
we have the x1 patch.
we have two other patterns x2 and x3 they are the same as x1 but with a different volatility
we consider the first 5 points to be patterns, all the following will be considered the space relatively to the pattern
1) bring the patterns into a single range, say 0-1
the usual normalization
all three patterns will be the same
now it is necessary to normalize the space relative to the pattern
this is done by the function r02
where " y " is space and "x" is not a normalized pattern
Then we connect the results of transformations from functions r01 and r02 in one row (vector)
and we obtain a pattern normalized in the range 0-1 and the space is normalized relative to this pattern
similarities should be searched not by correlation but by Euclidean metric
the smaller the value, the closer the patterns are to each other
Stop bullshitting and study the rocket. R is probably also there. Compare it with MSUA with your
The meaning of currency exchange is not in the mathematical plane, but in the profitability of the moment. What was in the past does not make any sense.
You can search infinitely for the meaning of machine learning. New circumstances will always be decisive. You have to look at the market on a different plane.
Stop bullshitting and study the rocket. There's probably one in R, too. Compare it with your MSUA.
This rocket is bullshit, the same spetral analysis, at least rsa, at least fourier, at least polynomials and svd from MSUA, the essence is the same, the results are the same...
We need to expand the feature space, the models lack information!!!
And if you divide those poor 10 candlesticks in the sliding window into 1000 components, nothing will change....
Try it.
The meaning of currency exchange is not in the mathematical plane, but in the profitability of the moment. What was in the past no longer makes any sense.
You can search infinitely for the meaning of machine learning. New circumstances will always be decisive. You have to look at the market on a different plane.
It's like saying "I'm for world peace" or "water flows, fire burns". You can't argue with that, and you're right, but in fact you're just talking in your ears.
Programmed by commands, not by philosophical thoughts...
this rocket is bullshit, the same spetral analysis, at least rsa, at least fourier, at least polynomials and svd from MSUA, the essence is the same, the results are the same...
We need to expand the feature space, the models lack information!!!
And if you divide those poor 10 candlesticks in the sliding window into 1000 components, nothing will change....
Try it...
I wanted someone to do it... I'll have to do it myself again