Machine learning in trading: theory, models, practice and algo-trading - page 1319

 
Maxim Dmitrievsky:

Well, just in case, that we do not just turn our tongues here :)

To be clear - I wish good luck to all participants in this thread. For the simple reason that on the signal neuroGraal I, with pleasure, will subscribe.

But, hell, considering that everyone here - Alexey and Sanych's grandson and the Teacher, etc., etc., work in absolutely different dimensions, making up some crap as they go along, do I have to wait until I die? And old man Asaulenko diligently supports this confusion and vacillation.

It makes me nervous and anxious.

 
Alexander_K:

To be clear - I wish all the participants in this thread the best of luck. For the simple reason that on the signal neuroGraal I, with pleasure, will subscribe.

But, hell, considering that everyone here - Alexey and Sanych's grandson and the Teacher, etc., etc., work in absolutely different dimensions, making up some crap as they go along, do I have to wait until I die? And old man Asaulenko diligently supports this confusion and vacillation.

It makes me nervous and anxious.

A simple solution seems obvious to me - to study the newest techniques of the Ministry of Defense. For this you need to get pumped up in simple architectures first

Next comes space with nice results.

Alexey chose not the worst catbust, one of the best for research, by far. It is used in CERN, for example, to analyze collider results... someone who deals with quantum randomness )

 
Maxim Dmitrievsky:

A simple solution seems obvious to me: learn the latest MO techniques. To do this, you need to get pumped up in simple architectures first

Next comes space with nice results.

Alexey chose not the worst catbust, one of the best for research, by far. It is used at CERN, for example, to analyze collider results... someone who deals with quantum randomness )

Well, I will wait - till the end of the year my patience should suffice :))

 

Forum on trading, automated trading systems and trading strategies testing

Machine Learning in Trading: Theory and Practice (trading and not only)

Aleksey Vyazmikin, 2019.02.12 04:00

However, I decided to conduct an experiment on the effectiveness of training on different proportions of training and test sample participating in the training. The step will be 10%, i.e. training sample in the beginning 90% and testing sample 10%, then the testing sample will gradually increase by 10%, each sample will have 200 models - let's see what comes out. Another question, how best to compare these combinations, the average or the absolute criterion - ideas are accepted.


Models are almost ready, will there be any ideas to compare them, or only flood?

 
Alexander_K:

It is absolutely clear to me from my personal correspondence that he found what he was looking for. I could be wrong, but he does not want to confirm or deny my words. He just won't get in touch. Well, let it be a forum legend :))

Mmmm... go to eternity guys go... first Yura Reshetov, then Kokos, then the investors ordered his son Alexa ....

no fun(((

 
Aleksey Vyazmikin:

The models are almost ready, will there be any ideas to compare them, or only flood?

I am studying the book in hated English, I want to show the unprecedented level of MO (perhaps, in the form of articles, in Python)

so temporarily purely an observer

 
The Grail:

Mm-hmm... the guys are going away into eternity, they are going away... first Yura Reshetov, then Kokos, then the investors ordered his son Alyosha....

no fun(((

The angry investors finally caught up with Alyosha's son, yes. His fate is unclear, as is Doc's. Alas...

 
Maxim Dmitrievsky:

I am studying the book in English, which everyone hates, and I want to show an unprecedented level of MO (perhaps in the form of articles, in Python).

so temporarily purely an observer.

Why hateful, on the contrary, tell the truth in foreign teachings hidden for idle people who are gathered here!

 
I think Alyosha and Doc might have survived the turmoil by literally flogging investors' physiognomies with their neural networks.
 
Alexander_K:
I think Alyosha and Doc might have survived the turmoil by literally flogging the investors' physiognomies with their neural networks.

Doc is most likely alive, just offended by numero uno and the fact that he drained bitcoins on Bitrex, but Alyosha and Jura are most likely really in the netherworld, and were probably there under violent circumstances. Here's an advertisement for Forex... It would be in theme, if somebody would sing something about how the market rises and breaks the guys, both stupid and smart, both cowards and desperate daredevils, something like Makarevich's "One day the world will bend under us".

Reason: