Machine learning in trading: theory, models, practice and algo-trading - page 2080
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
Pareto sets? It will be interesting to see.
I don't know what it is ((( I'm just starting))
Even for some simple task like binary classification of days - was there significant news during the day or not?
Obviously, the news should be taken into account somehow, but so far it is not clear how to formalize it all correctly.
The simplest one is the most obvious. Events - the time of news release and the market's reaction to it. The event can be one news item, but the model can consider other news items.
There are very profitable systems based on news that analyze statistics for forecasts\fact
If you find it, drop me a link.
Although it will be a hundred or more new features, for each type of news: forecast, reality, previous.
Well, you just have to deal with it, maybe sometime later
yuzzled the rocket?
You were using a rocket?
Not yet... let me enjoy my illusions. Just a bomb, by the description.
you're out of your mind))
There are two lines of code!
You can try to put the indicators, not just the price
You're out of your fucking mind!)
There's two lines of code!
I'll do it soon, after coffee.
You see, it's just a convolution used there. I wanted to take the course first, but the teacher is stupid and has not started it yet
What is max pooling and so on, it's not clear.
I'll do it soon, after coffee.
You see, it's just a roll-up. I wanted to take the course first, but the teacher is stupid and has not started it yet
What's max pooling and stuff, I don't understand.
Go to hell with these teachers, look at any online course, it's like trash, everything is already there!
max pooling is when all values in a particular convolution are replaced by the maximum value, if I'm not mistakenLet me show you a simple example.
How do you see a solution to this problem?
Anybody else have any ideas on how to do this, it's basically a grail, by the way. With this technology, you can make any cp smart and adaptive.
I don't know what it is ((( I'm just getting started))
It's just that optimization by multiple criteria in parameter space results in sets (Pareto) rather than individual points.