From theory to practice - page 372

New comment
 
Dr. Trader:

Atach has two files in the archive for the experiments. Both contain values in normal distribution, histograms are the same and almost symmetric with respect to zero.

But these files have one very big difference - their markness.
One file has memory (non-markovian process), you can try to predict "next value greater or less than zero" relying on past values. You can apply neuronics and other machine learning to predict.
The other file has no memory (Markov process), any prediction will fail. Machine learning is powerless, but maybe Alexander can predict something with physics.

Whoever will learn to determine which file has memory and which does not, will do well, and applying the same method to forex will finally prove that the price formation process is indeed Markovian.

Also it is worth checking if the normal distribution is a sufficient condition for profitability of the model. Make a random walk cumulative cumsum() graph and try to trade on it.

sample1

sample2

The difference is in asymmetry

 

This is what all sorts of BP transformations are done for, so that these distributions of the first difference, second difference, products of differences, etc. are strictly symmetric and contain an exponent.

Prepare your pockets, gentlemen!

 
Gentlemen) don't forget that the likelihood of a price being at a certain point says nothing about its future behaviour) take care of your pockets)
 
Gentlemen, we'll all have to move to Moscow and settle our differences face to face, over a beer and some pleasant Western music.
 
There is no friction) purely a scientific discussion) and the truth is in the equities)
 
Alexander_K2:

No, I can't. Another post.

It is the rednecks, "from the farm" as they are called, arming themselves with oscilloscopes, thinking that they have some healing signal in front of them, but only a little noisy, who bring confusion to the souls of the afflicted. Those who suffer believe them, and lose everything - money, flats, etc.

Gentlemen! Don't be lazy to think abstractly - look at probability density functions and draw conclusions. That's where it's all ours.

Vasyuki chess players listened to Ostap with filial love. Ostap was carried away. He felt a rush of new energy and chess ideas. (с)
 
Alexander_K2:

This is what all sorts of BP transformations are done for, so that these distributions of the first difference, second difference, products of differences, etc. are strictly symmetric and contain an exponent.

Get your pockets ready, gentlemen!

Do you mean that the graph looks very nice?

Which pair?
 

Shit...... What were the thoughts on preparing pockets for money....

Gotta keep at it - it can't end this way either... we need bargaining.

 
Who can tell me if the mobile version does not work with private messages? I promised to post a translation of the article on the forum, but I'm out of the house at the moment.
 
Novaja:
Can anyone tell me if the mobile version doesn't work with private messages? I promised to post a translation of the article on the forum, but I'm not at home at the moment.

Can you write in a nutshell what it's about?

1...365366367368369370371372373374375376377378379...1981
New comment
Reason: