Machine learning in trading: theory, models, practice and algo-trading - page 2011
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 cuts began to coincide +- with the tester... well, at least, if the real is not good, then in the tester too
For now it's trading since September 21, in the tester it's about the same. And for an earlier period in the tester it is good, but the weeks are unsuccessful (probably)
For some reason it is always good at the beginning of the week (after the "pre-training"), then it "drops", maybe just coincidence
found something else to improve, maybe it will finally work )
long fucking wait to catch bugs
on the long movements it pulls, on the U-turns stalls
here is an example of the tester (updated logic) the last 2 months
But it is worse with old logics. I may try to use new logics with a trader, I will freeze it next week.
What has caused the discrepancy?
So what was the reason for the discrepancies?
I do not know, they are still there, but not that big.
The error was in the upside down trader logic.
The cuts are starting to match the tester +-........
it looks linear, that's encouraging
Were there any such contests here in the thread?
I would like to use a sample with 3 target values, ........
You're doing nonsense imho, but good luck to you, who will participate there
looks linear, that's encouraging
in 5 months, it's a plane (in the tester, new logic)
If it finally works, I will share. Not much time yet.
I don't know, they are still there, but not that big.
the error was in the upside down trader logic.
Look towards OHLCV on the zero bar - maybe that's it?
I.e. your mistake when interpreting trade results (when writing the code)?
In 5 months, even the plane (in the tester, new logic)
If it finally works, I will share. Not much time yet.
It looks pretty good!
How is the input signal generated, on every bar or otherwise?You are doing nonsense imho, but well, good luck to you, who will participate there
Are you confused by the 3 values of the target?
Look at OHLCV on the zero bar - maybe that's it?
That is, your mistake when interpreting trading results (when writing the code)?
The logic there is already messy, it would be better to understand it (what I've copied myself). And why it works this way and not the other way?
That looks pretty good!
How do you generate the input signal, on every bar or something else?Yes. It's adaptive control with reinforcement, not a classic