Machine learning in trading: theory, models, practice and algo-trading - page 3239

[Forester]

As an option: a template in MQL will generate 5-10 thousand signs (OHLCVV, time (YMDHMS), mashki, zagzagi (non peeking), etc. with different parameters (2,3,5,10,15,15,20,20,30,30,50,50,100,200,300,300,500,1000)) - and our models will trade on them. Maybe only 5 out of 5000 will be used by the model, if it considers that they are enough.
Although non-tree models will take a very long time to learn. And the championship will become not about NS, but about trees/forests/busts)))))

[Aleksey Nikolayev]

fxsaber #:

It worked in the Marketplace.

Text and pictures are already enough.

• The world's first world championship in trading between artificial intelligences.
• An unperturbed cyborg against a background of charts and panicked stock exchange workers.
• Crisis? - Artificial intelligence is the future.
• A strong expert in machine learning? - Prove/test your competence. Embellish your CV with a world-class prize.
• Etc.

There will definitely be no shortage of viewers. Attracting experts is doubtful, but it happens. Specialists are more likely to say I don't have a TC. Encourage newcomers to the MoD - it's hard to say. What will definitely work is the number of sales in the Market of EAs with AI. I think additional Market sales would pay for the championship within a year. The budget for organising and running the championship is $250K, minimum. Prize money is a small part of the budget.

Still not the first, if you think about Numerai at least. It's hard to disagree with the rest.

[mytarmailS]

Forester mashki, zagzagi (non peeking), etc. with different parameters (2,3,5,10,15,15,20,20,30,30,50,50,100,200,300,300,500,1000)) - and our models will trade on them. Maybe only 5 out of 5000 will be used by the model if it considers that they are enough.
Although non-tree models will take a very long time to learn. And the championship will become not about NS, but about trees/forests/busts)))))

It looks like tying a crutch to another crutch

[Andrey Dik]

mytarmailS #:

I don't know what kind of traders this is aimed at.

It looks like 5 people will participate in the contest, 4 of which are metaquotes employees who worked on integrating them into metatrader.

I'll be there.

"less people, more oxygen"))))))))))))))))))))))))))))))))))

[sibirqk]

СанСаныч Фоменко #:

I have a real EA with R, with the first variant of which I reached the tester.

The structure is as follows:

1. There is an ordinary mcl EA with the usual set of functions: working with orders, stops, MM..... The block of signal generation, in the examples of metaquotes - crossing of two mashes, is replaced by an appeal to R, which sends the next OHLC.

2. The R code roughly speaking consists of two parts:

2.1. converting the OHLC into a bunch of predictors for the models. These are hundreds (or thousands) of operators in R with access to some packages (not models) from R.

2.2. the actual signal computation by the model.

3. The signal for trading is sent back to the Expert Advisor: -1; 0; 1.

Returning to the topic, it turns out that to use ONNX p.2.2 will be ONNX, and in the Expert Advisor will have to move p.2.1? This is a serious undertaking for me, as besides the models themselves, other packages from R are used, the algorithms of which will have to be coded in µl.

You seem to use wooden models, and in ONNX, as I understand, you can only save network models. So, in essence, it will be a network model champion.

[mytarmailS]

sibirqk #:

You seem to use wooden models, but in ONNX, as I understand, you can only save network models. So, in fact, it will be a network model championship.

That's not true

[sibirqk]

mytarmailS #:
Not true

What is?

[mytarmailS]

sibirqk #:

What kind of things?

Wooden models are fine

[СанСаныч Фоменко]

sibirqk #:

Which is what?

I've seen somewhere that you can put everything in ONNX that is available in the Scikit bible, and there are all sorts of models and quite a few.

[sibirqk]

mytarmailS #:
Wooden models are also possible

SanSanych Fomenko #:

I saw somewhere that you can put into ONNX everything that is available in the Scikit bible, and there are all sorts of models and quite a lot of them.

Well, I will not argue, I am not too strong in ONNX .