Machine learning in trading: theory, models, practice and algo-trading - page 989

 
Igor Makanu:

I now want to go from the opposite direction - there is non-random data, so the math apparatus should give a perfect forecast, and then you can make it more complicated

So, I'm not proposing to put a mapper on the data but to feed the data that should be processed by the mapper with a 100% guarantee.

i will have to try it in python, it's too slow in MT... maybe i will try it later

Even arima should be able to handle it

 

By the way, Mandelbrot's legacy is economophysics.

They have their own formulas and methods there, but I haven't studied them. It is postulated as a replacement for the obsolete theory of the efficient market.

The roots of economophysics lie in the works of the classics.Benoit Mandelbrot discovered in 1965 that the dynamics of financial series (price fluctuations in the stock exchange) are absolutely the same in small and large time scales: it's almost impossible to determine from the graph of such series, whether it represents price fluctuations during an hour, a day or a month. Mandelbrot called this propertyself-similarity, and the objects possessing it -fractals. Investigations of processes with such properties are very actively conducted in physics and analysis methods developed there often (unfortunately, not always) help to notice anomalies in behavior of financial series - the harbingers of sharp price collapses or rallies. The French mathematicianLouis Bachelier at the very beginning of the 20th century in his"Theory of Speculation" tried to describe the dynamics of financial series by analogy with Brownian motion - chaotic motion of molecules in a liquid or gas. Modern models which generalize such approach generate fractal processes which are statistically very similar to real financial series. Many of these models are based on the theory of chaotic dynamical systems - equations generating complexdynamics, sometimes almost indistinguishable from a random process - created in the 1970s-1990s. Modern econophysics also uses other powerful toolsof theoretical physics- for example, thecontinuum integral, the most important toolof quantum mechanics andquantum field theory. But perhaps the most fashionable trend today isevolutionary games, directly imitating the activities of countlessinvestors following one or another preference and principle.

Currently, an almost regular series of meetings on econophysics include: the NikkeiEconophysics Research seminar, and the APFA, ESHIA, Colloquium on Econophysics symposia.

 
Maxim Dmitrievsky:

I'll have to look it up in python, it's a pain in the MT... maybe I'll try it later

even an arima should do the job.

even measure it in parrotshttps://snob.ru/news/155663

In the cartoon "38 Parrots" while measuring the height of the boa constrictor, the heroes of the puppet show Monkey and Elephant made an inaccuracy, using different methods of calculation,saysthe resident of Ekaterinburg Stanislav Berezin

)))))

I'm interested in the math apparatus that can accurately recognize the Weierstrass function, and then you can go further ;)

В мультфильме «38 попугаев» насчитали на 26 мартышек и на 7 слонят больше
В мультфильме «38 попугаев» насчитали на 26 мартышек и на 7 слонят больше
  • snob.ru
мультфильме животные думают, как измерить рост Удава. Попугай предложил использовать себя в качестве единицы измерения: «Сколько в тебя попугаев поместится, такой у тебя и рост». Попугай отмерил 38 шагов, после чего измерения провели Мартышка и Слоненок: у первой получилось 5, а у второго 2. Станислав Березин считает, что животные использовали...
 
Igor Makanu:

even measure it in parrotshttps://snob.ru/news/155663

)))))

I'm interested in the mathematical apparatus that can accurately recognize the Weierstrass function, and then we can go further ;)

Recognize in the sense of writing: it is a v-m f-function, I am 90% sure?

I thought you had to predict it.

Where do you want to go next? I'm going to the pub.

 
Maxim Dmitrievsky:

I thought I was supposed to predict

Where are you going next? I'm going to the pub.

Yeah, you can predict.

Alas, I'm working at night tonight (((


I'm asking to give a mathematical model - here in the PM well-wishers say look for in the woods- so far I'll go there if there are no options (NS would throw structure who would - with the NS for a long time know, but apparently the hands do not grow from there - did not find anything there ((( ))

 
Igor Makanu:

Yeah, I can't predict.

alas, I'm working at night today (((


I ask to give a mathematical model - here in the PM well-wishers say look for in the woods- so far I'll go there if there are no options (NS would throw structure who would - with the NS for a long time know, but apparently not the hands grow from there - did not find anything there ((( ))

Well, lez is right, I gave an example here with multiplication table

 
Maxim Dmitrievsky:

well les yes, I threw an example here with the multiplication table

I would be glad if you give me a link to this example - alas, from your posts to find it or on the topic... random forest

 
Igor Makanu:

I would be glad if you could give me a link to this example - alas, from your posts to find it or the topic... the random woods are a mess.

in mt4 alglib seems to be built in too, but it's a slave to 5

Files:
RF_sample.mq5  4 kb
 
Maxim Dmitrievsky:

i think alglib is also built in mt4, but i'll switch to 5

Thanks, it'll give me something to do for the night.

I've already switched to 5 but if I get an order for something on the forums 99,99% of them are for MT4, so I do everything on MT4 without thinking - I know it's a bad habit, but I'm used to it and I'll start kicking myself :))

 
Maxim Dmitrievsky:

Yes, well, it is possible to fill in some intermediate values

The only thing I use in fractals is zechal symmetry and sometimes I get nice patterns with good inputs on the charts. But by hand, not automated in any way

like this one from the last one.

Sometimes multifractals also work - formations repeat one after the other but with different periods, the same as in the B-M function.


If I understood correctly, instead of a series of prices, I should use a series of fractals (I meant the indicator that uses fractals)?

What are multifractals?

Reason: