Machine learning in trading: theory, models, practice and algo-trading - page 3188

 
Aleksey Vyazmikin #:

If you think the market is random, then why waste your time - any model will not work, except by chance.

I don't think it's random, it is random. It's no different than a sb.

Not only will you not see the difference, but you don't understand what you are doing.
 
Maxim Dmitrievsky #:
I'm not the one who thinks he's random, he is random. It's no different than sb.

Then why are you wasting your time?

 
Aleksey Vyazmikin #:

Then why are you wasting your time?

On what? Exactly, why are you wasting your time on rubbish?)

Because you don't know what you're doing at all, absolute zero.
 
Maxim Dmitrievsky #:
On what? Exactly, why are you wasting your time on bullshit?)

Because you don't know what you're doing, you're a complete zero.

It's just another load of rubbish.

 
Aleksey Vyazmikin #:

More rubbish.

What are you doing? Explain it to yourself at least. At least 😀 every time before doing something, a person always asks himself this question unless he is an idiot. And the second question is why are you doing it 😁😁
 
Maxim Dmitrievsky #:
What are you doing? Explain it to yourself at least. At least 😀 every time before doing something, a person always asks himself this question unless he is an idiot. And the second question is why are you doing it 😁😁

Here's why you should think about what I'm doing. Sit and think, then write some justification for the conclusion based on your thinking, not profanity.

Learn to work systematically.

 
Aleksey Vyazmikin #:

Think about what I'm doing. Sit, think, then write some justification of the conclusion on the basis of your reflections, not profanity.

Learn to work systematically.

I wrote that you're doing bullshit. Absolute nonsense bordering on dementia.

That was in response to your question about results.
 
Maxim Dmitrievsky #:
I wrote that you were doing bullshit. Absolute nonsense bordering on dementia.

That was in response to your question about the results.

That kind of expression is good for reading poetry or selling cucumbers at the market.

Where is the constructive criticism?

 
Aleksey Vyazmikin #:

Thousands - there are too many computing resources needed - one pass is about 40 minutes - basic calculation on a video card.

In general, I thought that such a test allows only to check the possibility of such clusters at different ranges of the predictor.

But it is necessary to look at the probability of hitting a particular range of the quantum segment, which was initially selected.

And still I would like to hear the opinion on the question of difference of the target in percentage expression for reliability of such test.

Come up with a simplified calculation scheme for simulations.

For some (not absolute) confidence in meaningfulness, the result for real data should fall at least in the 5% tail of the sample (left or right). But the sample should be several thousand at least.

 
Aleksey Vyazmikin #:

With such expression it's good to read poetry or sell cucumbers at the market.

Where's the constructive criticism?

That's it. What's there to criticise?) Did you realise what you did and why? If you did, why did you ask on the forum?)

I see some attempts to put the numbers left after previous efforts somewhere.