Machine learning in trading: theory, models, practice and algo-trading - page 1097
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
I'm just freaking out over definitions that Brownian motion is sb, and generalized motion is not sb, hence the confusion.
Maybe I don't understand something in this life.
maybe ask Mike? he's an expert)
3. to test retrospectively on a sample of years up to 2010(10 years) a smaller timeframe(1min, 5, 15)
How do you mean retrospectively? ) backwards like this ?
Generalized Brownian motion was introduced by Mandelbrot through a generalization of the random functionX(t) (random walks) by replacing the exponentH= 0.5 by any real number from the interval 0<H<1.
Generalized Brownian motion is a class of Gaussian processes allowing the exponent H to take arbitrary values from 0 to 1.
What can this tell us? The point is that representation of price distribution in the Gaussian model (fig. 5) differs from the prices represented by the fractal model (fig. 6): high peak and thick tails. The function with normal distribution (i.e. Gaussian dependence) has index H = 0.5, while the function corresponding to the price distribution has index 0.5 < H < 1. It turns out that by introducing the notion of generalized Brownian motion, Mandelbrot has shown that the movement of currency pair prices is Brownian motion - ordinary or fractional, given the difference in the properties of the models. Depending on the value of H, the price can have persistent or antepersistent properties.
But this doesn't stop the series from being the SB?!?? the motion is still Brownian
http://www.forexcenter.ru/almazov2/
Generalized Brownian motion was introduced by Mandelbrot through a generalization of the random functionX(t) (random walks) by replacing the exponentH= 0.5 by any real number from the interval 0<H<1.
Generalized Brownian motion is a class of Gaussian processes allowing the exponent H to take arbitrary values from 0 to 1.
What can this tell us? The point is that representation of price distribution in the Gaussian model (fig. 5) differs from the prices represented by the fractal model (fig. 6): high peak and thick tails. The function with normal distribution (i.e. Gaussian dependence) has index H = 0.5, while the function corresponding to the price distribution has index 0.5 < H < 1. It turns out that by introducing the notion of generalized Brownian motion, Mandelbrot has shown that the movement of currency pair prices is Brownian motion - ordinary or fractional, given the difference in the properties of the models. Depending on the value of H, the price can have persistent or antepersistent properties.
But this doesn't stop the series from being the SB?!?? the motion is still Brownian
http://www.forexcenter.ru/almazov2/
Look, I'm not very knowledgeable on this subject, to be honest, I'm not knowledgeable at all ... but you say that the market is random, which is not true.
Market movements depend on the actions of market participants, on buying and selling right?
Of course it is, it turns out that participants make random deals, they lack reason and logic, so they are not people but atoms in boiling water that do something chaotically
Maxim, are your deals on the market random?
No, you train the net on the history and using the statistical advantage you open deals, I'm telling you, everybody does it, this is the so-called"market memory".
And there are also levels in the market, for example when you buy something at 100 the price squeezed and you were not closed by the stop at 99 and the price is now at 75 and you are sitting in a loss praying for the price to come back, when it comes back to 100 you have to close your buy, then you make a sale and the price falls. That's the level, not the extrema.
Of course, you won't be alone there, because the crowd would go in at the same points.
Nobody takes levels into account when they do Brownian motion tests.
Look, I'm not too up on this stuff, to be honest, I'm not up on it at all ... but you're saying the market is random, and it's not
I'm asking about terminology. Generalized Brownian motion is a SB or not, and why
Mandelbrot says it is. Thick tails from here are not an indication that the market is not random and is not SBI'm asking about terminology. Generalized Brownian motion is SB or not, and why?
Mandelbrot says yes. The fat tails from here are not an indication that the market is not random and is not the SBI do not know (I'm not an expert in this subject).
HI Maxim, I have already got the brownian motion ....
You copy the code if you want...it is called the "weiner's process" which is the basis of "Brownian Motion"Yes, I know. The question about generalized brownian motion with different H parameters. Is this a random walk
Yes, somewhat...But I have a complete code of random walk algo using "Monte carlo" simulation)))
You can't use RDF in random walk...:)))
So if the market is random too... )
Look, I'm not too up on this stuff, to be honest I'm not up on it at all ... but you're saying that the market is random, and it's not.
The market movements depend on the actions of market participants, on purchases and sales, right?
Of course it is, it turns out that participants make random deals, they are devoid of logic, they are not human beings but atoms in boiling water that do something chaotic
Well you've got an M5 TF on the screenshot, it means you've already hidden some of the M1 movements in the M5 bar, why?
I see a lot of examples of randomness on this forum, do you want to call it a coincidence? :
- we cannot guess when a big player will appear? - surprise?
- we can't guess the big player's target? - today 5 pips, tomorrow 10 pips - surprise?
- We look at the charts of currencies thinking that the players' goal is to make a profit on price movements, while at the interbank market they often come to buy currency and leave the market, the goal is merely an exchange, not price movements - unexpected?
Well, about the TF, let's return to examples: here's an internal combustion engine, we do not know its principles, and the sequence of ignition of the mixture 2-3-4-1- 2-3-4-1 does not seem logical and ... random? OK, we take TF M5 for this sequence, we got 1-1-2-2-3-3-4-4
well, what do we understand what an internal combustion engine is? - no, it was an incomprehensible mechanism for us, and still is, but we are sure that now it is not random.... and then engine frequency changed and instead of logical 1-1-2-2-3-3-4-4 we got 1-4-2-3-1-1-3-4 - again we need to pick up TF?
;)