Machine learning in trading: theory, models, practice and algo-trading - page 855
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
Spit on the predictors, and feed the normalized time series to the NS. The NS will find predictors by itself - +1-2 layers, and there you have predictors
I tried to use deltas from the 0th bar for 10-50 bars in the past. The error was at the level of 45-50%. The spread does not work with such percentage points.
How?
Tried to feed deltas from the 0th bar for 10-50 bars past. The error was at 45-50%. Spread cannot be worked with such percentages.
Everything works for me. But I don't make predictions, only classifications - like whether it's worth waiting for a profit on a trade or not.
Deltas, if correctly understood, are unnecessary, imho. Price BP itself, normalized.
Everything works for me. But I don't make predictions, only classifications - like whether it's worth waiting for a profit on a trade or not.
Deltas, if correctly understood, are unnecessary, imho. Price BP itself, normalized.
I thought you wrote that you still use information from the glass.
What is the error percentage in training and in real trading?
I thought you wrote that you still use information from the glass.
he wrote a lot of things, and each time it was different, Rena #2
again, you're cluttering up the whole thread.
and one picture he showed me, some bald scraps I can type a ton of.
instead of acting like a boy
I thought you wrote that you still use information from the tumbler.
Yes, but the NS doesn't play here. It's just the direct entry into the trade.
Let me remind you - I am on futures. But the tests on forex the system passes, Real on fx did not try.
Zy Yes, NS is only part of the system that makes decisions. The rest are standard, but my own indicators.
But, on NS only price BP.
What is your error rate in training and in real trading?
During training and tests 20-30%.
In real trading I don't know, I didn't count. It's quite acceptable.
Check it out, I got it out of contact. Very useful information as part of understanding the market!!!
Bifurcation point.
There is a special concept in thermodynamics that can be adapted to almost any complex dynamic system. From time to time any such system, be it a state, economy or human psyche, enters a critical state of uncertainty.
At this point the orderliness of the system is threatened and its further development can follow two possible scenarios: either disintegration to a chaotic state or reaching a qualitatively new level of orderliness. For example, the bifurcation point for the state can be called a period of political instability, for the economy - an economic crisis, and for a person - a traumatic event.
Check it out, I got it out of contact. Very useful information within the framework of understanding the market!!!
Bifurcation point.
There is a special concept in thermodynamics that can be adapted to almost any complex dynamic system. From time to time any such system, be it a state, economy or human psyche, enters a critical state of uncertainty.
At this point the orderliness of the system is threatened and its further development can follow two possible scenarios: either disintegration to a chaotic state or reaching a qualitatively new level of orderliness. For example, a bifurcation point for the state can be called a period of political instability, for the economy - an economic crisis, and for a person - a traumatic event.
Well done, Mikhail! We should return to entropy/non-entropy and its analysis. Put it on one of the NS inputs, and that's it.
Probably the most reliable way is to loop through combinations of predictors. But this is very long.
Look at the packagevarbvs . The package implements fast algorithms for fitting Bayesian variable selection models and calculating Bayes coefficients, in which the result (or response variable) is modeled using linear or logistic regression. The algorithms are based on the variational approximations described in" Scalable variational inference for Bayesian variable selection in regression, and its accuracy in genetic association studies" ("Scalable variational inference for Bayesian variable selection in regression, and its accuracy in genetic association studies" by P. Carbonetto and M. Stephens, Bayesian Analysis 7, 2012, pages 73-108). This software has been applied to large datasets with over a million variables and thousands of samples.
It selects predictors well and builds good models.
Good luck