Machine learning in trading: theory, models, practice and algo-trading - page 679
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
On the input - the purest increments and not just any, but through a strictly defined deltaT. And the sum of these increments is a probability amplitude. Having our stable distribution of increments and direction of the probability amplitude vector, the neural network should give ALL at the output.
That is, we are not predicting the price, but the center of the distribution, right? If so, it may be realistic.
That is, we are not predicting the price, but the center of distribution, right? If so, it might be realistic.
YES!!!!! I respect physicists!
That is, we are not predicting the price, but the center of distribution, right? If so, it may be real.
Any prediction/analysis makes an assumption based on historical data on which the training/analysis takes place. From which one should never expect very large coincidences. 60%-70% correctness of the assumptions is a pretty good result.
YES!!!!! I respect physicists!
Yes, but that's not what the public expects.) They will boo, they will throw stones.
Yes, but that's not what the public expects.)
That would have to be combined with the algorithm that works now. Alone both are not enough.
It is called instead of answering questions - it is easier to find the weakness of the opponent, but my questions have not disappeared :)
Sorry, I'm too good a psychologist for that.
Maxim, if you don't even understand what you are doing, what is the probability that you will understand someone else? Zero.
A weakness? Yes, that is your weak point: your complete and utter amateurism.
I'm ending this conversation. It is useless.
Maxim, if you don't even understand what you yourself do, what is the likelihood that you will understand anyone else? Zero.
A weakness? Yes, that is your weak point: your complete and utter amateurism.
I'm ending this conversation. It's no use.
As you like to write, who needs it he will understand from this dialogue what was meant and what conclusions can be drawn from it
further of course there is no pointFriends, have you noticed that this forum is becoming dumber and dumber on the set of participants? More you fight. In general, soon there will be no one to talk to. Only with Koldun about 60 degrees, ugh, i.e. 60% success in predicting.
Never mind. Every big topic on this forum ends up in a shambles. It's a common occurrence). That is, the topic seems to be nearing its logical conclusion.
Just this morning I wanted to start a new topic on the use of NS in TC. Something I thought, and did not - people only 2-3 people. Irrelevant.
Just this morning I wanted to start a new thread about the use of NS in TC. Something I thought, and did not - people only 2-3 people. Irrelevant.
Yes, I also wanted to start, but there is no topikstarter can not administer the topic at its discretion from the flood and changed my mind, zasratsya like this all sorts of talk about the R and library functions that lazy to filter out the grains of wheat, it would be nice if you could create a branch with administrator privileges, It would be nice if you could create branches with administrator rights, to leave only important posts, and to clean up demagogy and squabbles, this whole branch could be reduced to no more than 10-15 pages if to do it from the beginning, now no one will read from the beginning, and there's no sense, I say as someone who followed it from the beginning.