Machine learning in trading: theory, models, practice and algo-trading - page 1677
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
Whatever you say.
Suddenly I had an idea about another abuse. It looks something like this.
"Do you hear me?! You didn't leak as much as I did, so go read a book" and stuff like that. How does it feel? :-)
So Max, the point of reference is that there is Classification and Prediction and all methods can be referred to one group or another fundamentally and there is no third one at the moment. As soon as I come up with one, I'll be sure to let you know, but for now sleep well. We're all right, just each in his own way...
There is no "prediction. There is classification and regression, they are used as tools for prediction, what it is predicting is already an interpretation.
Clustering roughly divides a set of points into "piles", depending on density distribution and topology.Suddenly I had an idea about another abuse. It looks something like this.
"You didn't lose as much as I did, so go read a book" and so on. How's that feel? :-)
That's right, losing is the best teacher. A bank or a hedge fund is much easier to hire a trader who lost a couple hundred thousand dollars than someone who made a few grand and didn't lose it.
There is no "prediction. There is classification and regression, they are used as tools for prediction, what it is predicting is already an interpretation.
Clustering roughly divides a set of points into "piles," depending on density distribution and topology.Kesha, don't muddy the waters. Classification is determining a vector in one group or another. Forecasting is getting the future value of the desired value and this must be understood. I can't get enough of my video, because I explain all this in detail there.
There is no prediction I say. For MO it does not matter the essence of arguments, what is the time length, color, future, past, etc. There are intutes and outputs, it is not relevant to MO, you may as well make a dataset that approximates the past by the future, for example a series reversal, everything is the same, but it is not forecasting because the interpretation is different.
There is no prediction I say. For MO it does not matter the essence of arguments, what time length, color, future, past, etc. There are instants and outputs, it's not relevant to MoD, you may as well make a dataset which approximates past by future, everything is the same, but it's not forecasting...
It looks like we went to different schools....
No, you haven't studied at all, you haven't read any books, you haven't watched Vorontsov, and you just picked up clever words and expressions on forums.
No, you have not studied at all, you have not read any books, you have not watched Vorontsov, and you just picked up clever words and expressions on forums.
Once again, let's summarize for the young people:
Forecasting is getting the FUTURE value of the desired value. That is, getting a value that is not yet in the numbers.
Classification is a definition of the current state of the system. That is to determine which group the currently given vector belongs to. To this or that group.
Questions?
Both methods help to make a conclusion about the future..... or at least its probabilistic assumption.