Machine learning in trading: theory, models, practice and algo-trading - page 790
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
It's not that the topic has gone anywhere-it's "fuzzy. There is no regular moderation. Some pile, even worse than my thread.
But, we must wait for the man with the Grail to come to the forefront.
Waiting.
Waiting:
Something like that. But, with obligatory explanations - inputs/outputs, software used, etc.
You don't have to give away all the secrets - but the main things should be.
I got the same message. The nuance is that these NMR tokens will pay out in chunks for months, and the price of NMR is dropping.
And the Kaggle account has to be higher than a beginner.
p.s. There is some kind of mess going on there in the numeraire. Then the results sent a few hours before the end of the contest refused to be accepted and remained unprocessed. Or a model based on a randomly drawn set of predictors was suddenly "unoriginal", even though the chance for unoriginality was almost zero. It was also unclear about the stakes, and sometimes all of them were losing.
The feeling that twice a year they have a demonstrative update, everyone ran to buy their tokens and lost them in bets. And it goes around and around.
Mmmm, numaraai really something shady, they make you "play" in their fucking "stacking" which is completely idiotic to put it mildly (the risk is much higher than the profit), and they don't give prizes without stacking
And these are Michael's latest posts. The uniqueness of his approach, his out-of-the-box thinking,
the soulful openness to the world, sometimes it's fascinating. Michael, keep it up!
All this deserves the warmest words of support. But, Michael, it's time to move to the
But, Mikhail, it's time to move on to the next level! To implement your latest ideas you will need a different kind of computation.
Start python and bibbles and catch the code.
Welcome to the wonderful world of quantum computing!
It's hard for me to talk about it, but something made me decide to do it.
And it is the last posts of Michael. The uniqueness of his approach, his unconventional thinking,
the soulful openness to the world, sometimes it's just fascinating. Michael, keep it up!
All this deserves the warmest words of support. But, Michael, it's time to move to the
But, Mikhail, it's time to move on to the next level! To implement your latest ideas you will need a different kind of computation.
Start python and bibbles and catch the code.
Welcome to the wonderful world of quantum computing!
I absolutely agree and have thought about it. The future is in quantum....
You're waiting for that:
I am finally home and first of all I want to apologize for my long post which is simply impossible to read, but at that moment I was Chukchi, so I wrote what I thought without the punctuation marks and the spelling. I said what I wanted to say and some of the thoughts there are relevant. The main thing is to be able to understand them in such a not easy text.
Next... Here is the link to the blog where I posted what I had time to write on BO. Pay attention to the section "Approach to the instrument", where I suggest what I've done today. That is, the choice of initial conditions.
https://www.mql5.com/ru/blogs/post/717174
I am waiting for the corrections and changes. But let's agree on the following. If you with what you do not agree and think that it would be better to do otherwise, then you must present weighty arguments that do not necessarily have to be confirmation of practice or experience, will be sufficient logical conclusions (adequate reasoning) why you think to do so. No more verbiage, only a cold and reasonable calculation or proposal.
I propose to choose the initial conditions described in the "Approach to the tool", about which we spoke today and practically, it's just in this section described in more detail. And do not forget that this is a draft.
Tomorrow, if we agree on the initial terms and no one has objections, we will move on to the next stage.
I started writing another article on which I was prompted by the idea that it would be nice to have a methodology as in high school, where black and white would be written as possible to do, and how not.
The point is to find such methods that are applicable to both regression and classification and show relatively the same results. That is, general methods used in general in the field of machine learning. I just want to understand why most of the results do not satisfy them, and so far there is only one answer. You are deeply convinced that you are doing some step right, because it is logically explained and you read somewhere about it, but in fact what you do is wrong. IMHO of course ... Example I gave earlier with the size of the cage and the number of inputs. It is as though the meaning of simple. And now let's organize the whole process of training in my opinion and look at the results and compare. I'm not sure that I get a better result than yours, but it is worth a try. Since this will be a study and errors on my part will also be and thanks to the team and the emergence of disputes we will be able to get to the truth. It seems strange to understand that with such a variety of R packages in the ME field there is not a single one which would be robusta. Yes most of them are robust, you just do something wrong if there is no result. So check it, under my supervision :-) Although I'm not asking, but if there will not be any coders and generally these movements will not interest anyone, I'll go into the world of sports betting and will try it there. I've built betting models before but I want to try again with the new knowledge I've gained.
I would like to use the regression results in my article as well as the classification results. After this research I hope to obtain general methods for building similar systems. So it is like this. ...
Today is another day that's just a mess. My hosting provider suddenly went down and can not rise until now. Does not answer the UPU itself, as well as the company website and phone tech support. I hope ULTRAVDS will stand up and continue its work, but at the moment it dropped and no access to it :-(
As promised, I put the trading result at the moment of futures change and switching to summer time.