Machine learning in trading: theory, models, practice and algo-trading - page 3282
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
Another self-made one...
There is cross validation, everything is chewed and chewed..., widely used.....
That's the thing, cross validation may not work effectively here.
And what's the point of this self-design? Maxim flips the sample by chronology - assuming that the result will be identical - my experiment shows the fallacy. Or everything is individual and validation may reveal a random pattern or occurrence throughout the sample.
That's the point, cross validation may not work effectively here.
And where is this self-dealing? Maxim flips the sample chronologically - assuming that the result will be identical - my experiment shows the fallacy. Or everything is individual and validation may reveal a random pattern or occurrence throughout the sample.
don't move the arrows to Maxim, especially when he did not do or even think about any of the suggested things.
You shouldn't turn the tables on Maxim, especially when he didn't do any of the things you suggested.
What do you mean, he hasn't? Aren't you already training the model on the most recent history?
When no matrix can handle it.
It takes three seconds to find similar strings of length 30K in a string of 10M.
This is not counting all possible correlated patterns, but comparing the source with other data. You don't need a matrix, just a vector.
What do you mean I didn't? Aren't you already training the model on the most recent history?
I don't remember who picked on that first. Some nerd. It doesn't matter in my case.
I can't remember who picked on that first. It doesn't matter in my case.
How is your case different from mine?
How is your case different from mine?
because I don't like to communicate with illiterate sophists and psychologists )
such people do not produce useful content
because I don't like talking to illiterate sophists and psychologists )
Such people do not produce useful content
Does your "love" affect the data in some magical way?
This is not counting all possible correlated patterns, but comparing the source with other data. You don't need a matrix here, a vector is enough.
This is the core of the line-by-line calculation of the matrix.
This is the core of the line-by-line calculation of the matrix.
PearsonCorrM is 40-50 times faster than Algibov's line-by-line algorithm, probably even a fast homemade tool will not overcome such a speed gap.