Machine learning in trading: theory, models, practice and algo-trading - page 1799

 
mytarmailS:

I took a look...

the current file with the balance does not contain the prices, the prices that you sent me earlier did not agree in size with the current balance


UPD==============

If you think about it, the idea itself is a failure, it is necessary to analyze and predict not the balance chart, but the entry points for good/bad

I do indeed, in a strange way 52 bars disappeared from OHLCV history - I will try to analyze it.


It is necessary to aggregate the market conditions, the more successful trades - there is a growth, and the less successful ones - a fall. If you look at a specific entry point, it will simply be an additional learning of already existing conditions (analog of leaves).

 
Aleksey Vyazmikin:

The balance is needed to aggregate the state of the market, on which state there are more successful trades - there is growth, and where there are less - a fall.

If you look at a specific entry point, it will simply be an additional learning of already existing conditions (analogous to leaves).

Not quite right. There is no relationship / correlation of parameters to growth / decline. It seems to make sense to connect the rise / fall with entry / exit points / stops / trade direction.

 

Please help in solving a combinatorics problem!

There are N different unrepeatable elements, you need to take from them X element(s) at a time, with the input value being the number of the combination of all possible elements.

Is there a formula or function for this?

The input to the function should be an array with the elements, the number of elements in the combination and the number of the combination, and the output should be an array with the indexes of the elements.

Help me please!

 
Valeriy Yastremskiy:

Not quite right. There is no connection / correlation of parameters with growth / decline. It seems to make sense to correlate growth/decline with entry/exit points/stops/trade direction.

What parameters are we talking about in the correlation?

The fact that there may be different conditions for buy and sell trades I agree.

 
Mihail Marchukajtes:

For now on ssa, if you find something interesting, you can try to add prediction. The max lag is set in the settings. The numbers 1,2 are component numbers from 1 to max lag. The red dots are the strength of the component (1 is the most powerful and in descending order). The history section is selected by blue lines. The indicator is rebuilt only when you change the chart, number of components or vertical line, you can also rotate the mouse wheel.

PS what is interesting, the increments worked worse here.

Files:
axon.mq5  16 kb
 
Rorschach:

For now on ssa, if you find something interesting, you can try to screw prediction. In the settings you set the max lag. Numbers 1,2 are numbers of components from 1 to max lag. The red dots are the strength of the component (1 is the most powerful and in descending order). The history section is selected by blue lines. The indicator is rebuilt only when you change the chart, number of components or vertical line, you can also rotate the mouse wheel.

PS interestingly, the increments worked worse here.

Cool. From the soul to the soul :-)
 
Aleksey Vyazmikin:

Please help in solving a combinatorics problem!

There are N different unrepeatable elements, you need to take from them X element(s) at a time, with the input value being the number of the combination of all possible elements.

Is there a formula or function for this?

The input to the function should be an array with the elements, the number of elements in the combination and the number of the combination, and the output should be an array with the indexes of the elements.

Please help!

Maybe it will work

Or you can look at the paragraph "Combinations" in Okulov's textbook "Programming in Algorithms
 
Aleksey Vyazmikin:

What parameters are we talking about in the correlation?

I agree that there may be different conditions for buy and sell trades.

Optimizable parameters and growth zones of falling balance. The idea is not to optimize, but to take out meaningful characteristics for growth zones of falling balance, but the science says that it is difficult or impossible through any characteristics of BP in the presence of SB. And it is difficult to find mathematical models describing the series with sufficient accuracy, and it is not clear what size BP is needed.

Symmetrical conditions seem more correct to me. The series may also be reversed. ))))

 
mytarmailS:


It was a beautiful picture)))

 
Valeriy Yastremskiy:

It was a nice picture)))

It was a fake, I screwed up the code again

Reason: