Machine learning in trading: theory, models, practice and algo-trading - page 1891
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
After the corpuscular-wave dualism, there are many more interesting things to move forward. String theory, for example. Its different variants.
You are right.
It looks beautiful, have the new predictors been invented?
Yes! , what is the point of going through all kinds of AMO if the "backlash" in quality of recognition between them all is less than 5%. They all obviously lack information (signs) for deeper knowledge (better classification) of the object, so yes, I started working exclusively on signs and ways of presenting information.
By the way there is an interesting package in python on automatic generation of featuresfeaturetools, I unfortunately did not manage to run it in R-ka, some problems with python at me))) Look at it, I think the interesting thing.
Isn't it clear that it is NOT possible to define minima and maxima dynamically.
If it's even done a little further, late, there's no guarantee it's not a false reversal.
Don't say anything, don't embarrass yourself.
Sometimes people of kindergarten level really want to reinvent the wheel.
I would say try to invent
But so far there are no positive results in this direction
I would say try to invent
But so far there have been no positive results in this direction.
And there won't be.
Recently I made a virtual self-optimizer. It worked in conjunction with the standard tester.
In other words, it is testing normally, and as soon as the market closes (on Saturday) the virtual optimizer automatically goes on and selects the optimum parameters.
And the testing was done on real ticks, one week, one month, 3,6,9 months, one year, and even deeper. The optimizer connected not only every week, but also every 15 days, 1 month and 3 months.
And the conclusion is this: it doesn't matter which period you optimize for, 3 years or 3 months. The market and the behavior of currency pairs change randomly, no matter what was in the past.
Petros Shatakhtsyan:
In the early 80's with six employees of the research institute we decided to break (or destroy) the backbone of Sportloto (as Yusuf said about forex :).
One of us was a doctor of technical sciences, as well as candidates of science, mathematicians, professionals of different profiles in the field of development of computing complexes.
. . .
And there won't be.
I recently made a virtual self-optimizer. It worked in conjunction with a standard tester.
In other words, it was just testing, and as soon as the market closes (on Saturday) the virtual optimizer automatically goes on and selects the best parameters.
And the testing was done on real ticks, one week, one month, 3,6,9 months, one year, and even deeper. The optimizer connected not only every week, but also every 15 days, 1 month and 3 months.
And the conclusion is this: it doesn't matter which period you optimize for, 3 years or 3 months. The market, as well as the behavior of currency pairs, changes randomly, and it doesn't matter what happened in the past.
And all you had enough of optimizing on non-stationary process?????
And it won't.
Recently I made a virtual self-optimizer. It worked together with the standard tester.
I.e., the usual testing is going on, and as soon as the market closes (on Saturday) the virtual optimizer automatically works and selects the best parameters.
And the testing was done on real ticks, one week, one month, 3,6,9 months, one year, and even deeper. The optimizer connected not only every week, but also every 15 days, 1 month and 3 months.
And the conclusion is this: it doesn't matter which period you optimize for, 3 years or 3 months. The market, as well as the behavior of currency pairs, changes randomly, and it doesn't matter what happened in the past.
He has been trading on neurons for three years now. I spoke to him personally. He takes no less than 100,000 thousand accounts. Open his profile and look at all his accounts. He succeeded. So you can do it too. Don't give up.)
And it won't.
Recently I made a virtual self-optimizer. It worked together with the standard tester.
I.e., the usual testing is going on, and as soon as the market closes (on Saturday) the virtual optimizer automatically works and selects the best parameters.
And the testing was done on real ticks, one week, one month, 3,6,9 months, one year, and even deeper. The optimizer was connected not only every week, but also every 15 days, 1 month and 3 months.
And the conclusion is this: it doesn't matter which period you optimize for, 3 years or 3 months. The market and the behavior of currency pairs change randomly, and it does not matter what happened in the past.
He's been trading on neurons for three years now. I talked to him personally. He's been managing accounts for at least 100,000,000. Open his profile and look at all his accounts. He's done well. So you can do it too. You will succeed if you don't do it now. Don't give up.)
on the screen martin
Anything is possible )