Machine learning in trading: theory, models, practice and algo-trading - page 1541
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
the collective farm is called google
hehe... good answer )))
Companies like Yandex and Sberbank mostly use python for machine learning. Or rather, no one has even heard of R in production. In python, yes.
I would not compare myself with those who work for Yandex and Sber, and even more so with those who work for Google and Microsoft, there as they say "To Caesar the Rather", while here the saying "where you were born, you're needed" is more appropriate, that is if you started to deal with programming inthe Metatradertrading terminal in general, you must continue to use MQL, no matter what the fuck is going on in the world. In general, there is a strong feeling that in the same way as in the financial industry all are tricked, now the search engines are doing it, all are trying to bait over the finger, to let everyone on a fashionable and glamorous path straight to AD.
I would not compare myself with those who work for Yandex and Sber, let alone with those who work for Google and Microsoft; as they say "Render unto Caesar the things that are Caesar's", while with us the saying "Where you were born, you are welcome" is more appropriate. That is, if you started to deal with programming in the Metatrader trading terminal, then you should continue using MQL, no matter what the hell is going on in the world. In general, there is a strong feeling that in the same way as in the financial industry it is common to trick everybody, now the search engines are doing it, everybody is trying to bait over the finger and send them down the fashionable and glamorous path to the AD.
If they add modern ml libs in mql, then undoubtedly, although not for sure. Examples will still be very few in comparison. Moreover, there are only 2 people who understand it.
Or are you suggesting they rewrite them? Then it's not up to me
I'm not comparing myself with them, I'm saying that there's a lot of this stuff with examples. You take the ready-made stuff and apply it.
I threw it on the localhost, to test whether I wrote a normal tester in general. Monitoring in the profile
It's without considering spread and margap, but it's 15-minute symbols (signal by opening price), so I'm going to ignore margap at the moment. I will add them later.
I threw it on the localhost, to test whether I wrote a normal tester in general. Monitoring in the profile
Confirmation that it is this very TS
It's a tester without considering spread and marcaps. But it's 15-minute symbols (signal by opening price) so I've neglected marcaps for now. I will add more later.
Hi!
If you look at the screenshot, all trades are profitable. If so, they may be profitable. Or it is a testing data.
The bug was not in the code ))
without markups.
add a spread
some more
The bug was not in the code ))
without markups.
add a spread
a little more
Try on Moex, the spread is minimal there and if the method works, you will profit!
Try Moex, the spread is minimal there, and if the method works, you'll profit!
It seems that I somehow rewrote the logic from mt5 incorrectly. Not exactly the same. It should not affect the spread that much.
And there shouldn't be so many tradesIt seems that somehow I rewrote the logic from mt5 incorrectly. It is not exactly the same. The spread should not affect that much.
I mean the markup of the financial result or the simulated spread?