Probability theory question... - page 4
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
100%
vizit - you want an answer not about indicators, ask not about indicators :)
The task was not about the indicators!!!
Didn't look for any pitfalls...
Got the answer. Checked it out. It's exactly what I was looking for.
D1*D2*D3*(1-D4)*(1-D5)+...
Is this formula (or algorithm ) hard to implement programmatically?
Or maybe there are ready-made products for this kind of calculations?
D1*D2*D3*(1-D4)*(1-D5)+...
Is this formula (or algorithm ) hard to implement programmatically?
Or maybe there are ready products for such calculations?
There is a Lisp program that can simplify arithmetic and algorithmic expressions and differentiate (and the expressions themselves are not in Lisp, but in mathematical notation, the results too). It is called Maxima.
IMHO, this question is solved by Bayes' theorem. In fact, you can read more here - Bayesian networks of trust.
And here - download Genie is a freeware program based on Bayesian networks.
The most important postulate here: Bayesian network is a complete model for variables and their relations, it can be used to give answers to probabilistic questions.
D1*D2*D3*(1-D4)*(1-D5)+...
Is this formula (or algorithm ) hard to implement programmatically?
Or maybe there are ready-made products for this kind of calculations?
How do you know these D's?
I think this is the MAIN QUESTION
And what if the signals are not given by indicators but by people?
Indicators, absolutely all of them, apart from reflecting past price behaviour, do not say anything at all.
No indicator-based prediction is out of the question.
However, of course, this is my personal opinion.
The search of a magic indicator continues and sometimes takes very strange forms.
For example, there are cranks who calculate and compare the areas of geometrical figures formed by indicators.
And there are even fancier fantasies, e.g. people decompose the Price(time) function into a Fourier series in the hope of attacking a harmonic,
capable of predicting future price behaviour.
In short, the field of fantasy here is limitless....
Indicators, absolutely all of them, apart from reflecting past price behaviour, don't really tell you anything.
No predictions based on the indicator are out of the question.
However, of course, this is my personal opinion.
The search of a magic indicator goes on and sometimes takes very bizarre forms.
For example, there are cranks who calculate and compare the areas of geometrical figures formed by indicators.
And there are even more bizarre fantasies, for example, people decompose the Price(time) function into a Fourier series in the hope of finding a harmonic,
Being able to predict the future price behavior.
In short, the field of fantasy here is limitless....
I absolutely agree with you: an indicator will never predict the future. That is why there is only one way out: to understand (or see) the present, and based on the "understood" ( or "seen") to make current decisions. But this is my personal opinion.... ))
-
And regarding the options for solving the above described problem - everything is clear...
Thank you all!
Hehe, a rash statement... Given chart Close[n] = 2 + sin(n/20) (Close[n] - consecutive counts). It has the following signals: if Close < 1.2, buy with Take 1.79 and Stop 0.21; if Close >= 2.8, sell with the same parameters. Good signals that are never wrong.
I am not saying I have a solution to the problem of predicting the future. What I've written above is just a vague hint on the direction of research that I haven't even started.
A Close[n] chart is given = 2 + sin(n/20) (Close[n] is consecutive counts).
I am not saying that I have a solution to the problem of predicting the future. The above is just a vague hint at the direction of research, which I haven't really started yet.
Hello, Mathemat.
Yes, I should understand what " Close[n]" equals for EUR/USD for example, and I'm done :-)