Machine learning in trading: theory, models, practice and algo-trading - page 1523
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
An interesting book on the subject
Predictive Models: Explore, Explain, and Debug
https://pbiecek.github.io/PM_VEE/
Finally, we would like to signal that, in this book, we do show
-how to determine features that affect model prediction for a single observation. In particular, we present the theory and examples of methods that can be used to explain prediction like break down plots, ceteris paribus profiles, local-model approximations, or Shapley values.
- We use thesemethods to examine fully-trained machine-learning models as a whole. In particular, we review the theory and examples of methods that can be used to explain model performance globally, like partial-dependency plots, variable-importance plots, and others.
-charts that can be used to present key information in a quick way.
-tools and methods for model comparison.
-code snippets for R and Python that explain how to use the described methods.
On the other hand, in this book, we do not focus on
-any specific model. The techniques presented are model agnostic and do not make any assumptions related to model structure.
-data exploration. There are very good books on this topic, like R for Data Science http://r4ds.had.co.nz/ or TODO
-the process of model building. There are also very good books on this topic, see An Introduction to Statistical Learning by Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshiranihttp://www-bcf.usc.edu/~gareth/ISL/ or TODO
-any particular tools for model building. These are discussed, for instance, in Applied Predictive Modeling by Max Kuhn and Kjell Johnsonhttp://appliedpredictivemodeling.com/.
I have a peculiar thing, it's on its own mind... I have an interesting research on maximum entropy.
interesting study on maximum entropy i saw today, i liked how to use entropy for inputs determination (part 2 of the article)
What's missing in mine, apparently. I even came up with almost the same thing, but couldn't articulate it. And it's kind of backed up by theory.
It also shows that different markets are predicted differently, so if it's all in one pile... I don't know
https://robotwealth.com/shannon-entropy/
Back to the article. If you filter the noise by zigzag, this method clusters the signals almost perfectly. Plus it sort of shows the future, i.e. values are added to the front, so it can override the redrawing of the zigzag in some cases
The red one on top is a buy, the green one is a sell.
And this is how it was without the zigzag.
How can I replace the zigzag without overdrawing? What would binary signals show up / down 1; -1
Back to the article. If you filter the noise by the zigzag, then this method almost perfectly clusters the signals. Plus, it sort of shows the future, i.e. values are added to the front, so it may override the zigzag redrawing in some cases
The red one on top is a buy, the green one is a sell.
And this is how it was without the zigzag.
How can I replace the zigzag without overdrawing? What would binary signals show up / down 1;-1
Try this onehttps://www.mql5.com/ru/code/20143
I don't know how to check it, I wanted to get 1 - 0 signals, that's why I noticed it
try this onehttps://www.mql5.com/ru/code/20143
Well it's also a zigzag, it redraws at the end. And it is made incorrectly, it should be like this
Well that's a zigzag too, it redraws at the end. And wrongly made, should be so
the end always redraws, try my almost ZZ - almost because it is not so beautiful, but it does not redraw the tophttps://www.mql5.com/ru/forum/318267#comment_12508440
the end always redraws, try mine almost ZZ - almost because it's not as pretty, but it doesn't redraw the topshttps://www.mql5.com/ru/forum/318267#comment_12508440
Thanks, I will take a look
Thanks, I'll check it out.
here rewrote in podokono +1 and -1 outputs, the only thing is not tested as online works, but I think without problems
here rewrote in subcono +1 and -1 outputs, the only thing is not tested as online works, but I think without problems
I will test both of them later. This one only needs to display each bar, not only extrema
I will test both of them later. This one only needs to show every bar, not only extremums
Cool, thanks. I.e., it draws until the last bar, then there is no need to update the values?