Machine learning in trading: theory, models, practice and algo-trading - page 2270
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 to do?
where to fracture, catch points, make enough data of such fractures and train. but it requires a bit more resources than we have today.
https://arxiv.org/pdf/1806.08734.pdf
Ah, by grid I meant neuron, not martingale... well, yeah )
I couldn't get any meaningful answers, I just chewed on snot.
But okay.Ah, by grid I meant neuron, not martingale... well, yeah )
I shook all the local nerds and could not get any clear answers, all I could chew was snot.
Okay.Do you use dummies, do you calculate on the computer, do you know about expectation and variance? You know half about the cpu.
Look at the content and count how much of this list you don't know.
Or is there something concrete?
Do you use dummies, calculate on a computer, know about expectation and variance? You know about half of the cpu.
Look at the contents and count how much of this list you don't know.
Or is there anything specific?
A normal radio amateur is a person with a soldering iron and/or a programmer of specific devices. Their mathematics is very limited - mainly in order not to scare the immature minds with a theoretician. A typical example is that they call a correlation what is really an estimate of the correlation coefficient.
A normal radio amateur is a person with a soldering iron and/or a programmer of specific devices. Their mathematics is very limited - mainly in order not to frighten immature minds with a theoretician. A typical example - they call a correlation what is actually an estimate of the correlation coefficient.
Aleksey, don't be absurd, at least ...
Alexei, at least don't be absurd.
My opinion is the result of studying bourgeois books from the "bible of the cosnicker" (Eifice-Gervis, for example), so it is quite reasonable.
Econometricians are much more advanced in the theory, but also with their own specific quirks.
Do you use dummies, calculate on a computer, know about expectation and variance? You know about half of the cpu.
Look at the contents and count how much of this list you don't know.
Or is there anything specific?
Well, why haven't any of the local tsosopaths used bpf to find loops and analyze them? Because they don't know how? After all, only cycles are traded on the market. Well, sometimes trends. Or, it's easier to smartly draw pencils and write that this is a grail, like that half-wit with a cat on his avatar.
Ideally, we should make the series stationary, find cycles along the spectrum, and build a filter for these cycles.
How do you make them stationary? Correction for the average volatility by time of day? Logarithm and filtering?
How do you build a spectrum? The deeper the history is, the stronger the noise is, the weaker the signal can be. But everything changes on the market. If we take a short time span, there is no guarantee that it is a cycle and not a random coincidence.
I showed you my statistics on the spectrum
Ideally you should do ......
This does not work at all.
Cycles are like trends - if you see one, it's too late!
It does not work at all.
Cycles as well as trends - if you saw it, it's too late!
Yeah, I was just describing how the problem looks from this point of view.