Where is the line between fitting and actual patterns? - page 36
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
ZS Who is the forex director?
https://www.mql5.com/ru/users/profitabl
I see that the main criterion has a price - a tightly fitted formula will also fit the criterion. The "Stability Area" criterion allows you to choose a fit that behaves stably in some parameter area, which is intuitively acceptable. For me, the problem remains the same - did we manage to fit the parameters so tightly to the graph or did we find the parameters of the real regularity?
Forward is just modeling real trading: let's say another optimization shows that the period of the fast swing should be increased by 2, and the slow one - reduced by 1. Since these changes are small and fall within the "stability area", everything is OK. The system remains profitable. But such a system still needs to be found.
1) So the answer to the subject is obtained, especially as the author himself has shown us that he knows the answer to his question.
I don't think he's so sure he's right, otherwise he wouldn't be in the thread. Perhaps there is a more reassuring option for all of us.
2) Why don't we go back to that thread? That's what you created it for, after all, and a lot has settled down since then...
Not really, it's only about a selection of FP, and purely automatic, based on pseudo-formulas and on the zest of the day (well, I had to think of something urgent :))). This is a more comprehensive approach. And a lot of water has already flowed... It's OK if the topics overlap. Perhaps here we will find a result that will crown that branch as well?
3) I do not insist on my model. And I can easily accept any one that suits everyone.
The model in this context will not be one, much less a nyversal, everyone will take away something different to which they might find a use. And please don't throw any bOOS, bOOS2, etc. at our compliant minds. Let's just have Sample and OOS for now).
Forward is just simulating real trading: let's say another optimization shows that the period of fast mashkim should be increased by 2, and slow one - reduced by 1. Since these changes are small and fit in the "stability area", all is tip-top. The system remains profitable. But such a system still needs to be found.
aha, the primary objective is to find a system (a pattern), after which we are not afraid of fitting, but simply substitute optimal parameters?
I don't think he's so sure he's right or there wouldn't be a branch. Perhaps there is a more reassuring option for all of us.
Not really, it's only about the FN selection, and it's purely automatic, based on pseudo-formulas and the zest of the day (well I had to come up with something urgent :)). This is a more comprehensive approach. And a lot of water has already flowed... It's OK if the topics overlap. Perhaps here we will find a result which will crown that branch as well?
The model in this context will not be the same and even less so, everyone will take away something that may be of use to them. And please, don't throw all sorts of bOOS, bOOS2 etc. at our malleable minds. Let's just have Sample and OOS for now)
If there isn't a clear objective,
The assault will be drowned out,
We won't take the altitude..... ((
Forward is just simulating real trading: let's say another optimization shows that the period of fast swing should be increased by 2, and slow swing - reduced by 1. Since these changes are small and fit in the "stability area", all is tip-top. The system remains profitable. But such a system still needs to be found.
Then we'll go out at the end of the day.
There. That's the second type.
And, hey, I'm writing it down, too... :)