Discussion of article "Grokking market "memory" through differentiation and entropy analysis" - page 11

New comment
 
Олег:

As an option XGBoost is a source code library or even a simplified one:

https://habr.com/ru/company/mailru/blog/438562/

By the way, the article describes bousting, bousted backing

This one needs too much tuning, the article will be huge. It doesn't work well out of the box

Bagging is already present in these algorithms when trees are built.
 
At one time CatBoost was considered the most perfect, now XGBoost and Light GBM with a variant of the same algorithm XGBoost are ahead, so there is a choice. There is a lot of documentation on Light GBM in the network.
 
Олег:
At one time CatBoost was considered the most perfect, now XGBoost and Light GBM with a variant of the same algorithm XGBoost are ahead, so there is a choice. There is a lot of documentation on Light GBM in the network.

Well, you can put in any of them later, I've only dealt with catbust.

the funny thing is that the whole algorithm in python is less than 100 stock :)
 
Maxim Dmitrievsky:

Well, you can put in any of them later, I just had only dealt with catbusta

the funny thing is that the whole algorithm in python is less than 100 lines :)

Take a look at the hub article - 100 lines without boost libraries, otherwise you are the author - you choose.

 
Олег:

Take a look at the hub article - lines 100 without boost libraries, otherwise you are the author - you choose.

Well, simplified handmade is definitely no sense to take when there are full-fledged ones available

Anyway, as I make it so it will be :)
 
Maxim Dmitrievsky:
Anyway, as I make it so will be :)

right, waiting...

 
Thank you for sharing such an interesting idea and fine and thorough research and description, not to speak of a complete implementation! 
 
fxsaber:

At the same interval, the tester showed a different picture. But I would never take the tester's picture as adequate in this case.

It should be well understood that the tester shows complete bullshit at market entries in the mode at opening prices.

So do you think it is necessary to test only on ticks?

 

First of all, thanks to the author for the interesting research!

Unfortunately, when trying to compile I get 2 errors:

'virtual_optimizer' - unexpected token, probably type is missing? Auto_optimizer.mqh 47 18

'virtual_optimizer' - function already defined and has different type Auto_optimizer.mqh 47 18

Could you please tell me what is wrong here?

 
Verner999:

First of all, thanks to the author for the interesting research!

Unfortunately, I get 2 errors when trying to compile:

'virtual_optimizer' - unexpected token, probably type is missing? Auto_optimizer.mqh 47 18

'virtual_optimizer' - function already defined and has different type Auto_optimizer.mqh 47 18

Could you please tell me what is wrong here?

void  CAuto_optimizer::virtual_optimizer(void)

add type

1...456789101112
New comment