Machine learning in trading: theory, models, practice and algo-trading - page 2449

New comment
 
mytarmailS #:

What do you want to get out of it?

Increased stability of the TS during optimization. If there is some structure in the sequences of deals, it will be seen
 
Maxim Dmitrievsky #:
Increasing the stability of the TS during optimization
Do you want to make the capital curve as smooth as possible?
 
mytarmailS #:
You want to make the capital curve as smooth as possible?
Deals alternating randomly or not will show. I don't know what I want, I was just lying on the couch and randomly thought. The lower the entropy of the trades, the better the signal. No further thought has gone yet. Some kind of analyzer/optimizer for the TS maybe.
 
Another additional selection criterion for optimization, in general
 
Maxim Dmitrievsky #:
Another additional selection criterion for optimization, in general
I don't really understand the idea, so I won't recommend anything...
As for multi-criteria optimization, it's easy, there are a lot of algorithms for it
 
Maxim Dmitrievsky #:
Another additional selection criterion for optimization, in general

Maxim, you're not replying anywhere. So let me ask you here, will you be improving your Expert Advisor?

 
YURY_PROFIT #:

Maxim, you're not answering anywhere, so I'll ask you here, are you going to improve the advisor?

Life has taught you nothing))


 
elibrarius #:

Why balance and not funds? Funds drawdown is always worse than balance drawdown.

In normal TS equity and balance are almost the same, diverging within a trade. In fact, it's the result of the trade that matters, not what was in it.
 
Mihail Marchukajtes #:
In normal TS, funds and balance are almost the same, deviating within the limits of the transaction. In fact, what matters is the result of the transaction, not what was in it.
+
 

Is the average value of neural network weights, taken modulo, an indicator of the quality of its training?

Suppose there are two identical neurons, trained on the same data, one has a value of 0.87 and the other 0.23, which one is better trained?

1...244224432444244524462447244824492450245124522453245424552456...3495
New comment
Reason: