Machine learning in trading: theory, models, practice and algo-trading - page 2229
![MQL5 - Language of trade strategies built-in the MetaTrader 5 client terminal](https://c.mql5.com/i/registerlandings/logo-2.png)
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
For those who like to speculate on the mechanics of the market...
I trained the model to recognize the reversal point downwards, the model's output probability is from 0 to 1
The indicator (output) is shown in blue
In simple terms, the indicator shows sellers' interest in sales
As you can see from the picture, the indicator even works sometimes
But more interesting is something else ... All beautiful, vanilla "trends downwards" happen exactly when the indicator shows zero interest of sellers in sales
And as soon as the interest appears, the growth begins))
So you think why everyone is losing, why the TS is sinking, etc...
Nah... it looks like it's really fucked up.
About 5% of the people on earth are total fuck-ups. But for some reason all of them feel it is their duty to post on this thread
Catboost?
Forrest
There are about 5% of people on earth who are total fuck-ups. But, for some reason, they all feel it is their duty to post on this thread.
I have a different theory, exactly the opposite.
Edgar made a great point.
==============================================================
By the way, I don't know, maybe it was invented long before me, but with data simulation you can solve the problem of unbalanced classes in a sample, simulating missing amount...
Looks like it works fine
Forrest
I have a different theory, exactly the opposite
Edgar said it perfectly.
==============================================================
By the way, I don't know, maybe it was invented long before me, but with data simulation you can solve the problem of unbalanced classes in a sample by simulating the missing amount...
That seems to work fine
It's been around for a long time.
it's interesting to read idiots sometimes, but those 5% make me squeamish
It was invented a long time ago.
idiots are sometimes interesting to read, but the 5% are squeamish
By the way, how's your robot?
I never managed to make this idea work...(
By the way, what about your robot?
I never got that idea to work...
I mean, I couldn't get it to work. What idea?
I mean, it didn't work. What's the idea
well, with the simulation, the article on which your last....
I could not make new data work, maybe because I trained on 5 min, or maybe I wrote the wrong code
Does it work on your watch?
there are about 5% of the people on earth who are total fuck-ups. But, for some reason, they all feel it's their duty to post in this thread.
Do you count yourself among the 5% of total fuck-ups?
You also checked in on this topic, and only arrogance, no good from you. All of your efforts in this thread is nonsense and attempts to repeat the nonsense of other scholar-fuckers.
Have you come up with anything yourself?
+1
If you mean me, then you're full of shit again ))))))
I checked in this thread a long time ago, when you didn't even exist )))