Machine learning in trading: theory, models, practice and algo-trading - page 2524

[Aleksey Nikolayev]

secret #:
Calculate the ACF of the market already)

Use the market unsteady multiplication table)

[Iosebi Tavadze]

Sorry for the inconvenience. My indicator loads the system.

In electronics it is solved simply by setting a single oscillator that runs at the arrival of the impulse (the first candle). In this indicator and in others it can also be solved if you write an additional command string to turn on the indicator with the arrival of the first swarmed candle for a limited time. It means the indicator doesn't work during the candle's formation but after it is formed it is turned on for a limited time.

What do you think programming guru ------------ is it possible?

[secret]

Aleksey Nikolayev #:

Use the market unsteady multiplication table)

I've been doing it for a long time)

[secret]

LenaTrap #:

To be honest, I can't understand anything at all.

p.s maybe some super smart mathematician will take pity on me and explain what's going on here?

The formula is derived, out of sporting interest) it is unlikely to be useful for making money.

[Aleksey Nikolayev]

LenaTrap #:

To be honest, I can't understand anything at all.

p.s maybe some super smart mathematician will take pity on me and explain what's going on here?

Start with the simpler questions. For example, how do probability and frequency or expectation and sample mean relate to each other. Similarly, the ACF and the sample ACF relate to each other.

[JeeyCi]

LenaTrap #:

Okay, but then there is no need to count anything at all, because the random walk simply can not have any autocorrelation in principle, because I myself have created a random array of numbers, the generation of which was in no way related to each other. Why would there be a correlation that I didn't set? Nevertheless, it is useful to test the resulting series of numbers, and make sure of that, and at the same time test your estimation methods and their effectiveness?

But yes, we just have different ways of thinking, you think like an academic mathematician and I use computer simulation, these are different approaches to problem solving.

+1 don't do that kind of math...

only the current price determines the future price, "knowledge of past events does not help predict future movements"... that's the difference between real trading and simulation -- nothing randomly wanders in the market, everything is trivial -- sometime in the morning (or after LIBOR) all banks align their quotes (even regardless of what was, as well as regardless of what you can see in option allocations)... It's not the number of ticks per second (a simple VSA is enough here), but the schedule of the pit and participants...

Some have randoms, some have sb -- (some have theorized more than others, though some are even worse) -- but they can't tell factors from signs, so they go around the forest, some to the wood -- some are looking for dependencies, some are hoping for stochasticity and independence... to recollect formulas one more time...

Although the point of PRACTICAL application of ML is outrageously simple

There are basically three main differences between DL and Machine Learning.

1. DL gives excellent results on large datasets. But Machine Learning algorithms fail to process huge datasets. Machine Learning can work only on small dat asets. This is the limitation of Machine Learning. But DL can easily perform operations on large datasets.
2. In Machine Learning, you need to feed all features manuallyto train the model. But DL automatically extractsall the features. This makes DL much powerful over Machine Learning. Because manual feeding is a time-consuming process, especially if you have a large dataset.
3. Machine Learning can't solve complex real-world problems. But Deep Learning Algorithms can easily solve real-world problems. That's why many fields are using DL algorithms over Machine Learning.
   

-- it seems that all demagogues here choose to do ML by hand... except one person... so it's just out of the question to trade

p.s.

The only thing they can do here is to smartly direct a person (capable of doing a computational experiment) to Wikipedia with a stupid question "what's the difference between mo and average"... - and say it's a sporting interest (sending everyone instead of themselves)... thinking the smarter and more naive they are with this dumb question, the closer someone will lead them to a real trade... - pure Manipulation -- "count for me, trade for me, or else death" (they'll be cheating again, thinking that sheep become bulls in the market), not understanding where the market is and where their dialogue is ... it's dirty here on the branch

[Доктор]

Aleksey Nikolayev #:

As a result, after substitution, ACF=sqrt(min(j,k)/max(j,k)). If I didn't mess up something, of course).

I would also, if you don't mind, rewrite it in a more familiar form:ACF(t) =sqrt((n-t)/n), where n is the sample size.

[LenaTrap]

JeeyCi #:

+1 don't count like that...

Only the current price determines the future price, "knowledge of past events does not help predict future movements"... that's the difference between real trading and simulation -- nothing randomly wanders in the market, everything is trivial -- sometime in the morning (or after LIBOR is set) all banks align their quotes (even regardless of what was, as well as regardless of what can be seen in option allocations)... It's not the number of ticks per second (a simple VSA will suffice here), but the schedule of the pit and the participants...

Some have randoms, some have sb -- (some have theorized more than others, though some are even worse) -- but they can't tell factors from signs, so they go around the forest, some to the wood -- some are looking for dependencies, some are hoping for stochasticity and independence... to recollect formulas one more time...

Although the point of the PRACTICAL application of ML is outrageously simple

-- All the demagogues here seem to choose to do ML by hand... except one person... so it's simply out of the question to trade

p.s.

The only thing they can do here is to smartly direct a person (capable of doing a computational experiment) to Wikipedia with a stupid question "what's the difference between mo and average"... - and say it's a sporting interest (sending everyone instead of themselves)... thinking the smarter and more naive they are with this dumb question, the closer someone will lead them to a real trade... - Pure Manipulation -- "count for me, trade for me, or else you're done for" (they'll be cheating again, thinking that sheep become bulls in the market), without understanding where the market is and where their dialogue is.... it's dirty here on the branch

In the real market? Personally, I have some sort of philosophy:

*but I don't really want to discuss it, because it's useless to discuss assumptions without evidence.

[Доктор]

secret #:
Formula is withdrawn, out of a sporting interest) it is hardly useful for making money.

The situation is even worse. The formula seems to hint at the martingality of the series, and, as a consequence, the impossibility of earning.)

[secret]

Doctor #:

The situation is even worse. The formula seems to hint at the martingality of the series, and, as a consequence, the impossibility of making money )).

That's for SB. What do we need it for?)