Machine learning in trading: theory, practice, trading and more - page 808

Yuriy Asaulenko  
Alexander_K2:

One of the reasons is the complete lack of understanding of what should be fed to the input of the neural network.

I stand by my conviction - it is necessary to feed the BP increments to the input. But of what series? Of those ones that are in numerous tick archives? OPEN OR CLOSE? On M1 or D1? No answer...

If we consider that market processes are non-Markovian and cannot be predicted, then the main struggle should be to transform BP - trying to reduce it to a Gaussian process.

Hello Alexander!

Well, you are tired of your increments and reduction to the Gaussian process at the same time. I do not exclude that for your systems it is necessary, but generalization to all and everything is absolutely unfounded statements. In short, this is only your personal opinion, and no more than that. But do not impose it so insistently to all, as the truth in last instance.

I think that it is necessary to supply directly to the input of MO system a time series, normalized for a particular system. And I have already shown on the example of NS that it is both teachable and really works. Pictures of testing are given in this thread earlier.

However, this is probably not the only option, either.

Alexander_K2  
Yuriy Asaulenko:

I believe that the input to the MO system should be a direct time series, normalized for a particular system. And I have already shown on the example of NS that it is both trainable and really works. Pictures of testing are given in this thread earlier.

However, this is probably not the only option, either.

Yury, repeat again your pictures and experiments, because, by God, it's already not interesting to read the thread.

Yuriy Asaulenko  
Alexander_K2:

Yuri, repeat your pictures and experiments again, because, by golly, it is no longer interesting to read the branch.

That was before the New Year. There are many posts on the subject. Where do I find it now.))

In your branch recently showed a kind of good test-Graal (chart), a la Bollinger system (no NS). No increments. Only STO.

No implementation planned.

ZZY, though, there's something about NS in my blogs. There from the beginning of my classes, when I do not understand anything, to the moment when I decided on the use of NS.

Mihail Marchukajtes  

Here.... new turn

And the CU is rowing.

Pound and on the upswing.

¶ what's he gonna bring ¶

# A new turn #

♪ And you can't tell ♪

Until you turn it, around the bend.....

Mihail Marchukajtes  
Renat Akhtyamov:

I would feed just one parameter to the input of the neuron:

(high-open)/(open-low)

On periods of M30 and higher

You need to input what is the reason for price change, then any TS will work as it should. The price and everything that is built on it, including all kinds of distributions, are not the reason for the price, that is, by definition, cannot predict it. That's why you have these results..... IMHO...

Renat Akhtyamov  
Mihail Marchukajtes:

If you want to enter something that is the reason for price changes, then any TS will work as it should. The price and everything that is built on it, including all kinds of distributions are not the reason for the price, that is, by definition, can not predict it. That's why you have these results..... IMHO...

you don't know about my results, don't write

Mihail Marchukajtes  
Renat Akhtyamov:

You don't know about my results, don't write.

If you are feeding the input price or something from the price, and even from different TFs, then there is a possibility that you are unintentionally looking into the future. If you have a decent result, which is stable, etc. If the result is not stable, then most likely an accident.... Check everything very carefully, especially when you take data from other TFs

Mihail Marchukajtes  
Yuriy Asaulenko:

Do you know the reason for the price change? And what is it? And where do you get it to put it on the input?

I'll tell you right away - I don't know the reason for the price change. I'm at a loss for words.

Already tired to write. The delta volume and open interest are the reasons for the price. First the prerequisites for the movement are formed there, and then this movement starts.....

Renat Akhtyamov  
Mihail Marchukajtes:

If you are feeding the input price or something from the price, and even from different TFs, then there is a possibility that you are unintentionally looking into the future. If you have a decent result, which is stable, etc. If the result is not stable, then most likely an accident.... Check everything very carefully, especially when you take data from other TFs

I don't use neuronics

I may be wrong

I showed what Alexander_K asked, but then again I don't use it myself

But I support the open source, there's money to be made on it