Machine learning in trading: theory, models, practice and algo-trading - page 2722

New comment
 
Maxim Dmitrievsky #:
What? When was that?
I don't consider myself an MoD guru, it's a hobby.
It was a long time ago, but I remember everything.
 
mytarmailS #:
It was a long time ago, but I remember everything
On the contrary, I'm protecting you from leftist concepts and tricky teachings, but you don't appreciate it.
 
Maxim Dmitrievsky #:
I'm protecting you from leftist concepts and cunning doctrines, and you don't appreciate it.
No.
In sum, you say like this: you are all dummies, and all others are also dummies, and I am a dartagnan.....
 
mytarmailS #:
No.
The sum total of what you're saying is: you're all dickheads, and everyone else is a dickhead, and I'm a dartagnan....
No. I try to give facts first, that it's a road to nowhere. They start proving to me that it's not, I counter with other facts. People end up getting personal and then I troll them.
 
That is why I wrote that the object of research must be specifically defined, and the method of research follows from that. If the logic is initially broken, it is a way to nowhere.
 
Maxim Dmitrievsky #:
That is why I wrote that the object of research must be specifically defined, and the method of research follows from that. If the logic is broken from the beginning, it is a road to nowhere.

Answer the question logically: why none of the methods for BP does not work on the market if the market is BP.

But for any other BP these methods work, in fact, they were created for that purpose.

 
mytarmailS #:

answer the question logically: why no method for BP works on the market if the market is BP.

But for any other BP these methods work, in fact, they were created for that purpose.

Because it is possible to determine the cause-and-effect relationship there. In the market we are deprived of such an opportunity. We sit in the scales and look at how much they measure, but we can't know whether it is 5 kg of sugar, petrol or flesh, because there is no connection. We can assume, and we know for sure that if the weight has increased, something has been put on the scale, and vice versa.

 
Valeriy Yastremskiy #:

Because there you can determine the cause-and-effect relationship. In the market we are deprived of this possibility.

There are random VRs, they are also predicted without causality....

You say - so the market is a random VR + non-stationary.... OK, there are methods to make it stationary, but after that it's still not predictable....

 
mytarmailS #:

answer the question logically: why no method for BP works on the market if the market is BP.

But for any other BP these methods work, in fact, they were created for that purpose.

There is more randomness, you have to fiddle around to make it work.
 
Maxim Dmitrievsky #:
There's more randomness, so you have to fiddle around to make it work.

you can decompose the series into components, find the randomness, find the deterministic part. discard the random, leave the rest... A standard case for BP processing ...

But no, it doesn't work either.

At some point on new data, the random will become deterministic, and deterministic will become random....

So also NONE)

1...271527162717271827192720272127222723272427252726272727282729...3674
New comment