Machine learning in trading: theory, models, practice and algo-trading - page 993
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
Is it? And if you think about it, read your posts to you? Well, only eggs are cooler than Maxim.)
AAHAHAHA... That's very funny, thank you! Yes, a funny character, comic.
Yuri, I'm telling you again, the principle is right.
But, you see, this is the thing - even cool ideas do not resonate with people if there is no signal (like a passport) or it is negative like mine. I see it on my example - well, there is no positive balance....
But, you see, the thing is that even great ideas do not resonate with people if there is no signal (like a passport) or it is negative like mine. I see it in my own example - well, there is no positive balance, it would seem - pick up the banner, bring the work to the final, please people. No - no one is interested.
So in this case, too.
Well, no one has "equity in the sky," or even any equity at all, and that's it - the theme immediately becomes passé and uninteresting.
Conclusion: Each subject should simply have a "man with a signal". A positive one! Then life begins.
We are waiting for such a man. We hope and believe.
I must admit, I haven't seen it - I'm not interested in signals or even real-time reports. I do not see the point. I do not understand this universal desire.
Nah, I'm like a lot of people, I'm interested.
It's a measure of intelligence, no matter how you look at it. I, for example, have a man with decent signals among my friends. It inspires me, makes me work again and again, because I really see that it is possible to earn on Forex. I have been doing this for a long time and I`m sure it will be better in the foreseeable future.
Nah, I'm like a lot of people, I'm interested.
It's a measure of intelligence, no matter how you look at it. I, for example, have a man with decent signals among my friends. It inspires me, makes me work again and again, because I really see that it is possible to earn on Forex. And the fact that I personally can not do it - well, well.
I understand, you need external stimuli. You can't do it without them.)
The most important thing I forgot to say - this man, well, in no way uses neural networks.
I am absolutely convinced - if someone had demonstrated similar results in this thread, the whole forum would be dragged here, because NS is a funny thing. But, alas - without this important point, there is nothing to see or read here. IMHO.
I forgot to tell you the most important thing - this person, well, in no way uses neural networks.
I am absolutely convinced - if someone had demonstrated similar results in this thread, the whole forum would be dragged here, because NS is a funny thing. But, alas - without this important point, there is nothing to see or read here. IMHO.
Why not applicable?
why rhetorical?
PCA is a linear transform + reproducibility problems.
"Fourier transform, wavelets, spectral singular, etc. - decomposition algorithms
Tsne is an excellent dimensionality reduction algorithm for visualization. It needs the whole data set to work. It cannot work with new single data. It is possible (according to some sources) to adapt it for use not only with train/test sets but also with new single data by doing some complicated gymnastics. I haven't succeeded and I haven't come across articles with a successful Tsne implementation to lower the dimensionality of predictors in MO.
Rhetorical because apparently you haven't tried this algorithm. Otherwise you wouldn't have suggested it for dimensionality reduction... Although if you have results on this algorithm, please share.
Good luck
PCA - linear transformation + reproducibility problems.
"Fourier transform, wavelets, spectral singular, etc. - decomposition algorithms
Tsne is an excellent dimensionality reduction algorithm for visualization. It needs the whole data set to work. It cannot work with new single data. It is possible (according to some sources) to adapt it for use not only with train/test sets but also with new single data by doing some complicated gymnastics. I haven't succeeded and I haven't come across articles with a successful Tsne implementation to lower the dimensionality of predictors in MO.
Rhetorical because apparently you haven't tried this algorithm. Otherwise you wouldn't have suggested it for dimensionality reduction... Although if you have results on this algorithm, please share.
Good luck
Look, the person narrated a problem with too much data to classify, I suggested a solution...
PCA is also a decomposition algorithm, if I'm not mistaken, as well as others, just decomposition and reduction of dimensionality is achieved (something gets thrown out, and something gets left behind)
That all these algorithms will not give any benefit (except that they reduce the dimensionality), it is another matter and the question is not to the algorithms, but to the data.
Regarding tsne, maybe the algorithm is good, but on market data it works the same way as others, so I've tried to separate into classes, but I got nothing interesting, so I gave up. I don't know about new data, I've seen examples of tsne with train and test in the Internet, but maybe you also saw it
About tsne, maybe the algorithm is great, but on market data works as well as others, so I tried to divide it into classes, but nothing interesting is achieved, so I gave up. about new data I do not know, on the Internet I saw examples of tsne with train and test, but you probably saw it too
"PCA, Fourier transforms, wavelets, etc... of the new "t-sne". With their help you can make 5 inputs in ns out of 100 and almost have no loss in quality.