Machine learning in trading: theory, models, practice and algo-trading - page 2767

 
Amen.
 
Maxim Kuznetsov #:

for the last six hours, everyone is against the dollar.

Is this an evening pullback? Is it a reaction to critical news? Is it just a fluctuation, or did the Fed decide not to hike rates the day before?

No one who looks at just a quote on a single instrument will be able to answer that. From the point of view of an individual quote/sticker all options are equal.

PS/ about windows and reference points: from the point of view of 10-year bond holders, the 5000p rise in XAU today is a load of rubbish that is not worth mentioning. And someone must have lost their deposit.

This is not an analysis, not an analysis at all))))

 

Maxim Kuznetsov #:
    ..а нету обоснованной теории по которой что-то измерить, и почему 10, почему именно этих свечей,

why now, what was expected and how exactly GPT-5 helped.

even down to the elementary thing - "evaluating the result of the experiment". Without vs with GPT - how can it be evaluated? Whether the experiment was successful or not?

tomeasure - ...

and proving validity is something else entirely... proving a hypothesis through pvalue - .. .

but statistical significance in Bayesian approaches is unprovable (only in statistical approaches) -- prove the validity of Bayesian methods without statistics and you will have an article (you have no articles at all on your forum, only reading materials -- and there are a lot of screamers demanding articles (like essays in school, and the level of culture and quality of conclusions is lower than in school) == let them work further on their reading) ...

Bayes can only give you probabilistic decision-making

but probability != statistical significance of your hypothesis... and you have it (hypothesis)?

p.s..

and for autoencoder to work - yes, it should contain all possible classes, not just cats and dogs, by which it will not define crocodile.... - so the "sliding window" question is very vague....


p.p.s and timing too
SanSanych Fomenko #:

By my calculations, the window size ranges from 700 to 2000 bar. Predicting one bar ahead takes 35 seconds. If a blunt overshoot, i.e. increase the window from 700 to 1800 and select the optimal one, we get 420 seconds This is extremely long. Lots of things to optimise a lot, but requires other computers and the ability to load all cores.

Машинное обучение в трейдинге: теория, модели, практика и алготорговля - Используйте расстояние Махаланобиса вместо евклидового. Попробуйте использовать локальную регрессию, поскольку она позволяет сравнивать значимость
Машинное обучение в трейдинге: теория, модели, практика и алготорговля - Используйте расстояние Махаланобиса вместо евклидового. Попробуйте использовать локальную регрессию, поскольку она позволяет сравнивать значимость
  • 2022.09.17
  • www.mql5.com
понимает описание торговых условий частей-алгоритмов на естественном языке. попытался бы получить схожий результат с помощью более простых в реализации алгоритмов. те с фильтрацие по хорошим состояниям с точки зрения алгоритма
 
Maxim Kuznetsov #:

, XAU's 5000p rise today is complete bollocks, .

not bullshit, but running_to_security.... reasons in the media

 
JeeyCi #:

not bullshit, but running_to_security..... reasons in the media

and it is the translation of "reasons in the media" (twitter, facebook) into trade solutions that is the domain of DL and NN, they are made for that and are funded from that.... but we can't afford it :-(

 

small stop, big take ...

nothing else is needed, but 726 rules that were mined for two days, and this is only for sells )


 
mytarmailS #:


small stop, big takeout ...

nothing else is needed, but 726 rules that were mined for two days )

in light - an enlarged picture of the chart, from the point of view of the site :-))

everything in the world is relative and at the same time you can't hide anything.

PS/ 726 rules could not be mined - this is a breakdown of the eurosession.

 
Maxim Kuznetsov #:

in light - enlarged picture of the chart, from the site's point of view :-)

everything in the world is relative and nothing can be hidden at the same time


It glued the old picture for some reason, I'm fine when I enlarge all the pictures are correct.

Maxim Kuznetsov #:

PS/ 726 rules could not be mined - this is a breakdown of the Eurosession

Yeah, of course..... crossing of mashas yet tell me)))

 
mytarmailS #:

it pasted the old picture for some reason, I'm fine when I zoom in all the pictures are correct.

Yeah, of course the intersection of the mashes, tell me about it))))

Why not say - it can be reduced to mashki. But according to the presented screens, this is exactly it, the breakdown of the Euro session. There are such strategies and there are quite a lot of them, the general principle is to consider yesterday's trading session in its critical moments and trade from there. The EURUSD up trend starts when the US session ends above the high of the European session (ironclad definition of a trend).

but it will be a bit of a shame that 2 days of mining and CPU smoke comes down to a countable number of mashas in the end

 
Maxim Kuznetsov #:

Why not to say - it can be reduced to mashes. But according to the presented screens, this is exactly it, the breakdown of the Euro session. There are such strategies and there are quite a lot of them, the general principle is to consider yesterday's trading session in its critical moments and trade from there. The EURUSD up trend starts when the US session ends above the high of the European session (ironclad definition of a trend).

but it will be a bit of a shame that 2 days of mining and CPU smoke comes down to a countable number of mashas in the end

Are you serious or are you trolling?