Machine learning in trading: theory, models, practice and algo-trading - page 1989
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
because you have to connect the tester to the trader and use a pre-trained model at least a couple of weeks in advance. On cold runs it doesn't know anything at first
What does the lot have to do with it. I'm testing the errors.
I.e. while the bot's body is being prepared for stuffing )))).
And I thought you already had a trained bot. Just as I remember there were screenshots of the tests and they were quite impressive.
That is, while the body of the bot to prepare the stuffing )))).
And I thought you already have a trained bot. Just as I remember there were screenshots of tests and they were quite impressive.
They distract you with all sorts of R... I wish they would use a normal language where everyone uses it.)
Maybe I did something wrong...They are distracted by all kinds of R's... they could not just use a normal language that everyone uses.)
))), but who prevents? I personally decided (and it was a wrong decision) to port everything from C++ to MQL, the result was not bad, but the learning process was too long, because MQL is an interpreter after all and MT4 doesn't have good working with flows, so I had to give up))), but MQL was ported to C++, so I've decided to make the right choice from the very beginning, not to waste a year)))
Sometimes I wonder if I should mark a lag on training, because the result was really better when all mathematics was working in MQL, but )))) sounds crazy.
Or maybe I screwed up something too...
Greetings explorers, here's a rudimentary python tester. It may be useful for someone.
It accepts close price, spread, signals in range 0...1 where 0-sell 1-buy.
Trading is done by crossing the line 0.5. It is possible to decrease the trading intensity due to the insensitivity parameter that varies in the range of 0...25.
It runs arrays and plots balance and committed trades on the charts.
Nice balance curve on the tray...))
Greetings explorers, here's a rudimentary python tester. It may be useful for someone.
It accepts close price, spread, signals in range 0...1 where 0-sell 1-buy.
Trading is done by crossing the line 0.5. It is possible to decrease the trading intensity due to the insensitivity parameter that varies in the range of 0...25.
It runs arrays and plots balance and committed trades on the charts.
nice balance curve on the tray...))
Increase the track from 2 thousand bars to 20 or 200 thousand.I wonder what will happen. And add a test section.
yes
will you do it for me?
It will be more convenient, and the problem with "modules in one folder" will be solved in this miracle language)
Here is a simple tester in python. Maybe someone can use it.
Ooh, cool, thanks.
I remembered somewhere there was a talk about the archiver. Like if the file is compressed, there are patterns, etc. I can't remember where it was, I want to reread it.
Entropy archiver in yandex, here what glitchy link gets up. There are a lot of articles there.
https://habr.com/ru/post/180803/