Machine learning in trading: theory, models, practice and algo-trading - page 2212
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 do you mean you can't... well, you can split it up))
If one criterion is a global minimum of -1000, the other 0, and the third 150k
What do you want to add up there? )))))) you do not know what you're talking about
If by one criterion the global minimum is -1000, by another 0, and by a third 150k
What are you adding up there??? )))))) you don't know what you're talking about
don't make them infinite, put them in a range like all the others, from 0 to 1
so don't make them infinite, bring them to a range like all the others, from 0 to 1
No, Max, it does not work that way, optimization is a search for the unknown (functions, parameters, etc.)
To put "something" in the range 0-1, I need to have "something", I don't have it, I use optimization to find it
No, Max, it does not work that way, optimization is a search for the unknown (functions, parameters, etc.)
To put "something" in the range 0-1 I need to have it, and I don't have it, I look for it with the help of optimization
whatever... You have a function that needs to be maximized/minimized... everything
that's why all the healthy f-i's are in ranges. And you have a smoker's f-i.
whatever... You have a function to maximize/minimize... everything.
Listen, have you ever done a multi-criteria parameter search?
Listen, have you ever done a multi-criteria parameter search in your life?
I don't understand what you're doing. Draw a diagram.
I don't understand what you're doing, draw a diagram.
So you're training the neuron for "max profit". This is training for one criterion ( "max profit").
The man here, Alexander Alexanovich, says that neuronka finds the best solution "do not trade". Although I can't figure out how he did it, but okay...
So if the neuron decided "not to trade" So if the neuron decided "not to trade", then we have to add one more criterion (a minimum number of trades that the neuron can do): "min. number of trades".
It turns out that we already have to optimize by two criteria (or by 10)
You can't normalize anything here, because we don't know the final result
So you train the neuron for "max profit". This is training by one criterion ( "max profit").
Alexander Alexandrovich here says that the neuron finds the best solution "not to trade". Although I can't figure out how he did it, but okay...
So if the neuron decided "not to trade" So if the neuron decided "not to trade", then we have to add one more criterion (a minimum number of trades that the neuron can do): "min. number of trades".
It turns out that we already need to optimize by two criteria (or by 10)
It is impossible to normalize anything here, since we don't know the final result
I think that's the problem
when no one understands anything, but they start building from the top.
that's why there are courses on neural networks for nerds.
I think that's the problem.
when no one understands anything, but they start completing it from aboveprobably....
========================
made a large test sample
in the square is the piece of the test (new data) that I showed
Anyway, for 5 minutes, it eats up the commission
But it is possible to synthesize interesting models
It is necessary to include the training of the model in the fitness function at once and check it on shaft and test samples
So far I have made everything very confusing.
probably....
========================
made a large test sample
the square is the piece of the test (new data) that I showed
Anyway, for 5 minutes, it'll eat up the commission.
But it is possible to synthesize interesting models
It is necessary to include the training of the model in the fitness function at once and check it on shaft and test samples
I have made everything very confusing so far.
cp, they are not clear