Machine learning in trading: theory, models, practice and algo-trading - page 2056

 
Maxim Dmitrievsky:

Oh, my gosh...

what?

 
mytarmailS:

What?

Tags say randomly sampled, that's all
 
Maxim Dmitrievsky:
Tags say randomly sampled, that's all

Ahh, I think I realized that I do not understand what you mean and was talking about something else )) sorry

what video are you talking about ?
 
mytarmailS:

Ahh I think I figured out that I didn't understand what you were talking about at all, and I was talking about something else )) sorry

what video are you talking about ?
In all of them, it's the same thing. I will write an article if everything is ok. I will have to check it in the mt tester as well.
 
Maxim Dmitrievsky:
Yes, in all of them, it's the same thing. I will write an article if everything is okay. I should also check it in my mt tester.

Maxim, how does it close deals? I mean, do you set take and stop? Or does it close deals by itself?

 
Maxim Dmitrievsky:
Tags say randomly sampled, that's all
Something self-learning, like in the earlier articles?
 
Aleksandr Alekseyevich:

Maxim, how does it close your deals??? I mean, do you set a take and stop, or does it close by itself??? Or by time?

On reversed signals, flip-flop
 
elibrarius:
Something self-learning, like in the earlier articles?
Just tags are sampled randomly, with different retention times. Then it can be bruteforced
 
Maxim Dmitrievsky:
Yes, in all of them, it's the same thing. I will write an article if everything is OK. I will have to check it in the mt-tester

Have you tested it in the tester yet?

 
Alexander Alexeyevich:

not yet tested in the tester?

Just sat down, parser wrote

Here is the model, you need to feed it with 15 last increments, on each bar. The increments are counted as price minus 5-period oblique average. Send to the function double catboost_model(const double &features[]), which is in the inluder

If the signal is greater than 0.5 then buy, if less - sell. The time frame is 15 minutes.

I've been studying it since September 1 till now.

I will not do it anyway... i'll just leave it here ))

Files:
cat_model.mqh  9 kb
Reason: