Machine learning in trading: theory, models, practice and algo-trading - page 2797

New comment
 
Uladzimir Izerski #:

I'll wait for a more substantive reply, not a reply.

So you can write a reply to a whole book, and you say: you didn't answer, the answer is not meaningful, it's a reply)))).

So read my previous post again, but slowly and thoughtfully.
 
mytarmailS #:
That's how you can write a response to a whole book and your response is : you didn't answer, the response is not substantive, it's a retraction))))

So read my bullshit post again.

If the wording "self-respecting person" doesn't suit you then what other questions. Gee-gee)

 
Uladzimir Izerski #:

If the wording "self-respecting person" doesn't suit you then what other questions are there. Gee-gee.)

..

 

Forum on trading, automated trading systems and testing trading strategies

Is there a pattern in chaos? Let's try to find it! Machine learning on the example of a specific sample.

Aleksey Vyazmikin, 2022.10.21:46

Actually, I suggest downloading the file at the link. There are 3 csv files in the archive:

  1. train.csv - a sample, on which you need to train.
  2. test.csv - auxiliary sample, it is allowed to use it during training, including merged with train.
  3. exam.csv - a sample that does not participate in training.

The sample itself contains 5581 columns with predictors, the target in 5583 column "Target_100", columns 5581, 5582, 5584, 5585 are auxiliary, and contain:

  1. 5581 column "Time" - date of the signal
  2. 5582 column "Target_P" - direction of the trade "+1" - buy / "-1" - sell
  3. 5584 column "Target_100_Buy" - financial result from buying
  4. 5585 column "Target_100_Sell" - financial result from selling.

The goal is to create a model that will "earn" more than 3000 points on exam.csv sample.

The solution should be without peeking into exam, i.e. without using data from this sample.

To maintain interest - it is desirable to tell about the method that allowed to achieve such a result.

Samples can be transformed in any way you like, including changing the target sample, but you should explain the nature of the transformation, so that it is not a pure fit to the exam sample.


 
Aleksey Vyazmikin #:

You take the package rattle:: rattle() from R, it gives answers to all the questions in the post and to a lot of additional and useful questions, you are surprised by the results and tell us briefly about the results .

Rattle has everything: preprocessing, graphical representation of predictive ability of predictors, 6 models, model evaluation .

You have to spend a little less time to get results that are surprising to you than to post on the forum. But it will be your result, your knowledge and skills, not someone else's.

Otherwise, let's go to the market and you will be happy, though paid.

 

Forum on trading, automated trading systems and testing trading strategies

Not the Grail, just ordinary such - Bablokos!!!!

Aleksey Nikolayev, 2022.10.11 21:16

If you suddenly think about it, here is a good book on the basics of R and as a reference book.


If what I can discount)))) For me this one is better than others)))

 
СанСаныч Фоменко #:

Take from R package rattle:: rattle() it gives answers to all the questions in the post and to a bunch of additional and useful questions, you yourself are surprised by the results and tell us briefly about the results .

Rattle has everything: preprocessing, graphical representation of predictive ability of predictors, 6 models, model evaluation .

You have to spend a little less time to get results that are surprising to you than to post on the forum. But it will be your result, your knowledge and skills, not someone else's.

Otherwise, let's go to the market and you will be happy, though paid.

Here and prove that you are capable of something, and not just shake the air here - there was no evidence from you of the presence of completed solutions, only a statement that you have found a grail way of selecting predictors. I feel that your rattle is just a toy - not much use for a complex sample like this one.

I just suggested such a task in the form of a competition, so that not to shit on each other, but really could show their skills and thus get respect.

 
Aleksey Vyazmikin #:

Prove that you are capable of something, instead of just shaking the air here - you haven't given any evidence of complete solutions, only a statement that you have found a grail way of selecting predictors. I feel that your rattle is just a toy - it is not much use for a complex sample like this one.

I just suggested such a task in the form of a competition, so that not to shit on each other, but really could show their skills and thus get respect.

You should not "feel" but post the code and code results.

Very greedy! And greedy because of laziness.

$500 and all the answers. And then you lie on the couch and "feel" with a lighter pocket, but with the result.

 
СанСаныч Фоменко #:

You shouldn't "feel" it, you should post the code and the results of the code.

You're very greedy! And greedy because of laziness.

$500 and all the answers. And then you lie on the couch and "feel" with a lighter pocket, but with results.

So don't be lazy - try to solve the problem!

And about feeling, I write from the fact that I tried it, and either I used it incorrectly or it is really no use on complex samples.

I have my own method of extracting useful information, so I want to compare it with others.

 
mytarmailS #:
You follow, but you don't understand anything...(

For example what - to solve any problem you need a criterion for solving the problem, it is also an error))))


Now I noticed that you have completed the post. So I will allow myself to answer.

You are looking for nothing but errors. Therein lies the problem with MO dreamers. Looking for errors, not for specific prediction results. Even the smallest mistake is 100%_a mistake.)) In financial markets first of all.

Keep being wrong))) I will not answer and interfere any more.

1...279027912792279327942795279627972798279928002801280228032804...3585
New comment