Machine learning in trading: theory, models, practice and algo-trading - page 1514

 
Igor Makanu:

Here's more interesting material about entropy, so to speak the author explained on his fingers

https://habr.com/ru/post/171759/


I can't find something about decision trees, some fragments of information are on the web, I need something in the form of literature

yeah, i think it's a good article, i think i've seen it before.

well, the book from the random forest bata may need to be read immediately

i ran out of points on the site, i can't download)

https://www.twirpx.com/file/2130647/

Breiman L., Friedman J., Stone C.J., Olshen R.A. Classification and regression trees [PDF]
Breiman L., Friedman J., Stone C.J., Olshen R.A. Classification and regression trees [PDF]
  • www.twirpx.com
Boca Raton: CRC Press, 1984. — 366 p.The methodology used to construct tree structured rules is the focus of this monograph. Unlike many other statistical procedures, which moved from pencil and paper to calculators, this text's use of trees was unthinkable before computers. Both the...
 
Нейросеть из стекла сможет распознать образы без камер и алгоритмов
Нейросеть из стекла сможет распознать образы без камер и алгоритмов
  • votes: 1
  • ugpressa.ru
Научными сотрудниками из Висконсинского университета, расположенного в Мэдисоне, представлен прототип, так называемого, "умного" стекла, способного моментально запоминать и распознавать изображения и при этом без всякого рода камер, процессоров, или подключения к сети Интернет. В основе революционного стекла лежит удивительно доступная...
 

recognition at the speed of light - not bad

 

This technology is about 50 years old. It is nothing more than another application.

 

I made an indicator on the principle from the article about maximum entropy (the assumption that the system always goes in the direction of maximizing the etr.) Red for buy, green for sell. Which one has more value and goes in the trend.

I will check it, but it looks no worse than MAs.

I looked at kodobase, no one has done it.


 
Maxim Dmitrievsky:

I made an indicator on the principle from the article about maximum entropy (the assumption that the system always goes in the direction of maximizing the etr.) Red for buy, green for sell. Which one has more value is the trend.

I will check it, but it looks no worse than MAs.

I looked it up on kodobase, I don't think anyone's done it.

It's cool. It's noisy, though...

 

Good afternoon.

There is a pattern that I see with my eyes, but I cannot code it due to its complexity and not quite a clear understanding of what I see. The core is understood and formalized, but there are details that are caught by "lateral vision", are considered, but are not transmitted to the consciousness. The pattern has been successfully traded with my hands for many years.


I would like to teach the neuronku to see it (more precisely the part that set-up 1) to solve two problems:

1) to take out what she saw, to understand "what she was hooked on" in the set-up and through this better understand what I see and what exactly the characteristics of the graph are important.

2) To transfer the trade to it, or (a minimum variant) hang a bell.

The question to the pro, tell me if the problem is set correctly, and where to move to solve it?

P.S. I am calm about the fact, that it will be necessary to spend a year or two for the decision and even more calm about collaboration with pros.

Files:
q-pic.PNG  15 kb
 
Biqvi:

Good afternoon.

There is a pattern that I see with my eyes, but I cannot code it due to its complexity and not quite a clear understanding of what I see. The core is understood and formalized, but there are details that are caught by "lateral vision", are considered, but are not transmitted to the consciousness. The pattern has been successfully traded with my hands for many years.


I would like to teach the neuronku to see it (more precisely, the part that set-up 1) to solve two problems:

1) to take out what she saw, to understand "what she was hooked on" in the set-up and through this better understand what I see and what exactly the characteristics of the graph are important.

2) To transfer the trade to it, or (a minimum variant) hang a bell.

The question to the pro, tell me if the problem is set correctly, and where to move to solve it?

P.S. I'm calm about the fact that it will have to spend a year or two for a solution and even calmer to work with a pro.

I think it will not be easy to find five such gaps in a row. Maybe it is better to take a picture from the graph in the place where this set-up is present. Or better yet, take several pictures.

 
Alexey Viktorov:

I think it will not be easy to find five such gaps in a row. Maybe it would be better to take a picture from the graph in the place where this set-up is present. Or better yet, several pictures.

The picture is just an illustration of phase 1 and 2.