Machine learning in trading: theory, models, practice and algo-trading - page 561
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
What is seed responsible for? I don't remember anymore... for the number of signs, right? I use alglib forest
Holy shit!
I'm discussing canonical random woods, and you're an impromptu from under Novgorod!
Holy crap!
I'm discussing canonical random woods, and you self-made from under Novgorod!
I checked, they work :) only the error RMSE give out somehow strange, in the format 0.00000000000000005, I do not even know what to multiply it or divide, that would be readable was
Imagine how cool it is... you don't need hated R to fetch, isn't it a dream? to fetch in the cloud?
Well, okay.
There's a story. We took the NS (MLP), and we want it to find entries into deals. The algorithm of transaction support is known. Where when and how to enter trades - complete uncertainty. The task is to make a profit.
Your actions. With what and how will you teach? What will you enter?
Yuri's getting a little rowdy here... And what is the question?
I repeat - neural networks in the form in which there are printed articles are not able to predict anything in principle, so - just to play and kill time. Need some giant of thought, which would shake this kindergarten mathematics, then - maybe.
PS About the entrance - to the very point.
Yuri's getting a little rowdy here... So what's the question?
I repeat - neural networks in the form in which there are printed articles are not able to predict anything in principle, so - just to play and kill time. Need some giant of thought, which would shake this kindergarten math, then - maybe.
I've had Hs for a couple of months already)).
I checked, they work :) only the error RMSE give out somehow strange, in the format 0.00000000000000005, I do not even know what to multiply it or divide, so it would be readable
Imagine how cool it is... you don't need hated R to wipe, isn't it a dream to wipe in the cloud?
Random forest is that what Breyman came up with. And you have to prove with reputable people that what is written is exactly random forest. Everything else is a bicycle, from commercials, called "random forest," even in the cloud.
I'm not discussing the subplots.
Good luck!
No, well, you are not an ordinary comrade, I realized it long ago :))))))))
Well, okay.
There's a story. We took the NS (MLP), and we want it to find entries into deals. The algorithm of transaction support is known. Where when and how to enter trades - complete uncertainty. The task is to make a profit.
Your actions. With what and how will you teach? By the way, what will you use for input?
You may find the teacher's markup methods in the same articles. Why is it so unclear for you? Looking into the future, you can accurately determine which input will be profitable and which will not.
This method may be interesting (as something new), but it is described in few lines, which may lead to even more questions. You should describe it once, but in more detail, for example in your blog.
The teacher's methods of markup are in the same articles. Why is it a complete uncertainty for you? Looking into the future you can determine exactly which entry will be profitable and which will not.
But, in general, your method of teaching random values can be interesting (as something new), only you describe it in a couple of lines, which raises even more questions. Describe it once, but in more detail, in a blog for example.