Machine learning in trading: theory, models, practice and algo-trading - page 2511
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
Very fast. Through memory exchange. Not files or pipettes.
That's a good thing.
That's a good thing.
Explain why you are fighting for these milliseconds and wondering all the time whether it's fast or slow?
Explain why you're fighting for those milliseconds and always wondering if it's fast or slow.
I trade in minutes, in a fast market, so I know that in a second the price can go more than I have a mathematical expectation.
Have you tried this one?
Have you tried this one?
I had just recompiled my Expert Advisor today and it got an error. I have corrected it and shared it.
No. I have that program integrated into my EA, I don't see the point in changing anything, because it does everything I need.
I had just recompiled my Expert Advisor today and it got an error. I have corrected it and shared it with you.
I got it, thank you
Are there guys here who knows how to pass at a high level - ajax, get, post requests.
Or maybe there is a place to read, preferably in Russian
I trade in minutes, in a fast market, so I know that in a second the price can go by more than my expectation.
It makes sense.
What is the target, how did you find it?
Have you tried screwing in a trall?
If you just look at the error balance (+1 right -1 wrong for class 1), is the result much different?
I found a target with signs by brute forcing on the grid.
Yes, I have such an idea, I'd like to attach a trall, and use the trailing stops. I am writing now, but it seems to me it is not a panacea.
I do not quite understand what you mean. Please, describe the experiment in more details.
The target with the signs was found by brute force over the grid.
How is this? I'm thinking the same way about searching through the grid, so I'm interested in the methodology already implemented.
Yes, I have such an idea, I want to add trall and use trailing stops. I am working on it now, but it seems to me it is not a panacea.
It may sometimes appear as a crutch that pulls the strategy close to negative mathematical expectation.
I'm not quite sure what you mean by that. Could you please elaborate on the experiment.
I mean the metric, sometimes I evaluate a model not by profit but by the dynamics of correct class predictions. Essentially the same balance, but the change is fixed. The point is that the strategy can be affected not only by classification accuracy, but also by fluctuations in market volatility, and we need to look at the dynamics of classification accuracy without monetary expression.