Machine learning in trading: theory, models, practice and algo-trading - page 1681
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
Today I have read, there is no clear definition of AI, it is thinking like a human, it is the realization of decision-making functions... But the reason is different, actually there is no clear definition of human intelligence... In general it is better to agree on concepts first)))
There is a clear definition of intelligence (whether artificial or not)
Look for the lectures "COB" by General K. Petrov, a lecture about intelligence, there is a definition.
UPD...
Here it is
The intellect is a self-modifying, self-adaptingalgorithm for the selection and transformation of information, the result of which is the emergence of information modules previously unknown to the subject and not received in finished form from the outside
2) the market peeks at the traders' decisions and simply moves the price in the direction that benefits their minority and keeps the difference between their winnings and the losses of the majority.
For all its conventionality, the second option seems more true to me. Of course, there is no practical use in this. Except to conclude that the grail is impossible)
I think you have most accurately described the market from a scientific point of view.
And here's another question, I've already racked my brains, so to speak))
How to consider the market trading process from the point of view of the Sprague-Grandy functionhttps://habr.com/ru/post/124856/
There is a lot of material on the web with examples, even tic-tac-toe!https://e-maxx.ru/algo/sprague_grundy
What do I need to think about the elementary game in terms of trading strategies?
There is a clear definition of intelligence (whether artificial or not)
Look for the lectures "COB" by General K. Petrov, a lecture about intelligence, there is a definition.
UPD...
Here it is
intellect- a self-modifying, self-adaptingalgorithm for the selection and transformation of information, as a result of which there are information modules previously unknown to the subject and not received in finished form from the outside
Speech in general, if the definitions, terms, concepts have not yet settled and are understood differently, it is better to explain in more detail what is meant ... There will be less swearing.
In the '90s, I wrote a little program in Basic, a hint, what to do, a yellow icon appeared, press F5, appeared green, find and open the black closet, like that.... the manual called it a prog with elements of AI))))
I look at you and realize that we are in different galaxies, if not universes.
Let's go over it again:
Prediction is getting the FUTURE result of the sought value
Classification is the assignment of input vectors to one group or another.
And this is the difference between the two approaches.
ARE THERE ANY MORE QUESTIONS, OR DO I HAVE TO SAY IT AGAIN?
It's not my fault that you are stupid and can't understand elementary russian words.....
how to consider the market trading process from the perspective of the Sprague-Grandy functionhttps://habr.com/ru/post/124856/
there is a lot of material on the web with examples, even tic-tac-toe!https://e-maxx.ru/algo/sprague_grundy
what should one even imagine for the elementary game as applied to trading strategies?
Determining market conditions, predicting and forecasting are difficult to imagine as a game. Something similar is possible, but uncertain number of players, lack of clear understanding of market events influence on the market, other factors like weather pandemics wars, their influence on market members, influence in any case is probabilistic.... In general the application of game concepts and strategies for market, weather, Brownian motion is limited for me.
I look at you and realize that we are in different galaxies, if not universes.
Let's go over it again:
Prediction is getting the FUTURE result of the sought value
Classification is the assignment of input vectors to one group or another.
And this is the difference between the two approaches.
ARE THERE ANY MORE QUESTIONS, OR DO I HAVE TO SAY IT AGAIN?
It's not my fault that you are stupid and can't understand elementary Russian words.....
No, Michael, it's you who made up your own definitions, which are at variance with generally accepted definitions. Understand that "forecasting" can be called modeling of a wide range of quantitative characteristics of the FUTURE, and it can be done as a classification (growth/decline), as a regression (price, magnitude of change) and even clustering (what kind of market condition will be (will continue)). But there is no prediction in MO, the specific algorithm does not care what you put into it, if there is time and your aspirations.
No, Mikhail, it's you who made up your own definitions, which are at variance with generally accepted definitions. Understand, "forecasting" can be called modeling of a wide range of quantitative characteristics of the FUTURE, and it can be done as a classification (growth/decline), as a regression (price, magnitude of change) and even clustering (what kind of market condition will be (will continue)). But there is no prediction in MO, the specific algorithm does not care what you put into it, if there is time and your aspirations.
If there's no prediction in classification then it won't be.
Now smart guys, give me a list of directions and I will assign each of them to one of the two groups I listed. Fish crucian game has begun, and you are already really starting to piss me off....
I think you have described the market most accurately from a scientific point of view
And here's another question, I'm racking my brains so to speak )))
How to consider the market trading process from the point of view of the Sprague-Grandy functionhttps://habr.com/ru/post/124856/
There is a lot of material on the web with exampleshttps://e-maxx.ru/algo/sprague_grundy
What should I imagine for the elementary game?
I see a problem with this approach being applied to a two-player game. It is not very clear whether it can be generalized to games with an arbitrary number of players. In the market, there is no clear and immediate sense of confrontation between traders (unlike chess and other one-on-one games) because there are so many of them. And there is a significant difference even between games with two and three players - it's enough to play "backgammon" with different number of players), and the theory gets more complicated there...
With the market everything is somewhat simplified because everyone has only two strategies (buy and sell) and all traders are the same - it is called a symmetric binary game. In a symmetric game there is always a symmetric (possibly mixed) equilibrium:
I look at you and realize that we are in different galaxies, if not universes.
Let's go over it again:
Prediction is getting the FUTURE result of the sought value
Classification is the assignment of input vectors to one group or another.
And this is the difference between the two approaches.
ARE THERE ANY MORE QUESTIONS, OR DO I HAVE TO SAY IT AGAIN?
It's not my fault that you are stupid and can't understand elementary russian words.....
I look at you and realize that we are in different galaxies, if not universes.
Let's go over it again:
Prediction is getting the FUTURE result of the sought value
Classification is the assignment of input vectors to one group or another.
And this is the difference between the two approaches.
ARE THERE ANY MORE QUESTIONS, OR SHOULD I SAY IT AGAIN?
It's not my fault that you are stupid and can't understand elementary russian words.....
AGAIN?