Machine learning in trading: theory, models, practice and algo-trading - page 1225
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
Thank you very much.
But first of all before you start doing anything at all in this field, download and make sure you read the book "The Supreme Algorithm" by Pedro Domingos, which is very funny and simple (for geeks, it's like a "gabrahabro") It describes the principles of machine learning, what it can do and why it can't do. In my opinion, this is the best place to start. Since everything is simple and understandable. And my head is in order:)
Cool, thanks. I would also like to see a model (trend-flat) from Innocent...
Cool, thanks. I would also like to see the model (trend-flat) from Innocentius...
Wow, what kind of mysterious model is that?)
Vizard_: You're reaching for new knowledge, well done, and Kesha either shy or just stingy, here such do not like Kesha, be easier ...
Cool, thanks. I would also like to see the model (trend-flat) by Innocent...
Here is my model of a flat trend
I just pass the robot from the zero bar and analyze the sum of movements on BUY or SELL if the potential movement in any direction does not overcome the threshold of 75%, I calculate the type of flat - strong (70-75%) expressed (60-70%) weak (50-60%).
The line itself is not a zig-zag. It is not redrawn. It always stays as it is. The point is that I can correctly identify flags and trends and it will be true for any TF, regardless of what TF the analysis took place.
It works best for me and I'm not using it for trading, but for calculation of adaptive trall.
This is the model I will attach to the neural network as a tool for analyzing information.Here's my flat trend model
beautiful
Here is my model of a flat trend
I just pass the robot from the zero bar and analyze the sum of movements on BUY or SELL if the potential movement in any direction does not overcome the threshold of 75%, I calculate the type of flat - strong (70-75%) expressed (60-70%) weak (50-60%).
The line itself is not a zig-zag. It is not redrawn. It always stays as it is. The point is that I can correctly identify flags and trends and it will be true for any TF, regardless of what TF the analysis took place.
It works best for me and I'm not using it for trading, but for calculation of adaptive trall.
This is the model I will attach to the neural network as a tool for analyzing information.So what's the point? It is obvious that it is not a zigzag because it misses tops and probably it does not overdraw because it lags. If the purpose of the screenshot is not to demonstrate the lazy drawing of the model, it is enough to show the points where it really signaled the start of a flat or trend, but not to flipper the chart.
What's the use? And it is obvious that it is not a zigzag, because it skips tops and probably does not redraw, because it lags. But if the purpose of the screenshot is not to demonstrate the lazy drawing of a model, it is enough to show the points where it really signals the start of a flat or a trend, but not to shuffle the chart.
If I look at the chart, I'll see what I've got and what I've got.
For answers like yours, I made it clear that I don't use it FOR TRADING.
It's not about use, it's about performance, and if it's not there either, screw it.
It's not about usage, it's about operability, and if that's not there either, then screw it.
You see that little rectangle over there - that is exactly what I have described here.
And since you probably do not understand much about "working capacity", I can only sympathize with you.
If you think that an algorithm will appear and, well, it will work. universal for everything and everywhere You're very wrong.
And as you can see... or maybe not... What's written in the red rectangle is fully consistent with the situation on the market.)