Machine learning in trading: theory, models, practice and algo-trading - page 3661
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 highlighted is the most important.
It's been my foundation for years.
BUT.
It's no use.
OOV and OOS are fine. And if you run in a tester or simulate a tester in R by moving the window one step forward, the result has nothing to do with OOV and OOS.
Sad. this is exactly the result that does not depend on the preparation of predictors.
What it looks like on the OOS is how it works.
A couple of active accounts. There are more of them, costing different models.
Models are generated at a rate of one in 10 seconds :) Not hft, for managing normal deposits more.
This is from reals graphics.
I do not understand, you can be congratulated on finding "it",
or it is all untested from all sides and can not say anything for sure yet?
I don't understand, are you to be congratulated on finding "it",
or is it all untested from all sides and nothing can be said for sure yet?
It's just my hands are crooked
As a proof of "straight" hands: screens of OOB, OOS and, most importantly, the result (screen) of a step-by-step run WITHOUT OOB and OOS. And, it would be good to have the classification error on OOV, OOS and VNU.
As a confirmation of "direct" hands: screens of ALE, AOC and most importantly - the result (screen) of a step-by-step run WITHOUT ALE and AOC. And, it would be good to have the classification error on OOV, OOS and VNU.
Two years ago, I dumped everything here
Without the comment you made above.
I haven't counted, I'll have to go to the vps again. I'll look at it tomorrow.
The models are different, so I don't emphasise it.
So how many pips do you average per trade?
On 10 MAs, training period.
No tuning, just started, 5 sec.