Machine learning in trading: theory, models, practice and algo-trading - page 1678
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
Let's recap for the young people:
I think we need to educate young people with slogans, just like before!
Step by step - you will reach your goal!
Well, roughly got it... complicated
I agree, but even Bacon recommended using the way of the bee)
He's all washed up today )) Magician, Ale, give me the presents.
What gifts if you confuse magicians with conjurers))))
Clustering - only with a teacher.
Clustering - with or without a teacher.
Any TS - predicts, the horizon of forecasts is equal
It's been written about a hundred times...
So sit with the cormorants)))
Any TS - predicts, the forecast horizon is equal to
It's written about it a hundred times ...
That's right.
I'd say more on the MoD part:
what we want to get from the forecast is our wishes, but any way of data processing can only get a model similar to the original data,
that is - a miracle will not happen, so what can MO partially reliably predict, this is an example - the weather forecast, because there is a periodicity and repeatability
But if the markets had recurrence - 99% of indicators would work, you just need to find the right period
If the markets had recurrence - patterns would work
If the markets had "worked" - it would be at least in the ratio of 3 to 2, but practice shows that everything works 50 to 50 ((!)
What gifts, if you confuse the Witches with magicians)))
Clustering - only with a teacher.
Clustering - with or without a teacher.
Any TS - predicts, the forecast horizon is equal
It's been written about a hundred times...
So sit with the cormorants)))
So show me the clip again, where you did clustering... and what you clustered... and whether clustering
So show the clip again, where you clustered... and what you clustered... and whether clustering
This won't do you any good, you can't do proper
preprocessing (in the past we didn't discuss the input at all, we were just picking
In the last cartoon there was a correlation
matrix- showing the min lin dependencies between the inputs
(there are other dependencies as well), the algorithms are fresh,
Not more than two years old. The results are average to great.
As in all new rattles there is a random component
(can be removed). For interest rattle more...
That's right.
I'd say more on the MoD part:
what we want to get from the forecast is our wishes, but any way of data processing can only get a model similar to the original data,
that is - a miracle will not happen, so what can MO partially reliably predict, this is an example - the weather forecast, because there is a periodicity and repeatability
But if the markets had recurrence - 99% of indicators would work, you just need to find the right period
If the markets had recurrence - patterns would work
If the markets had "worked" - it would be at least in the ratio 3 to 2, but practice shows that everything works 50 to 50 ((()
Forecasts are different from forecasts. Weather forecast on the basis of recurrence was made the year before last. Nowadays we make diffusions with powerful machines based on data from weather stations. The problem of accuracy, as a rule, is only a lack of measurement points and computing power.
The market is significantly different in that there are no equations describing it (despite the claims of some comrades). If there were such an equation, it would be gone - like Winnie the Pooh's honey)
Forecasting is not the same as forecasting. Weather forecasts based on repeatability are a thing of the past. Nowadays, diffusers are solved by powerful machines based on data from weather stations. The problem of accuracy, as a rule, is only a lack of measurement points and computing power.
The market is significantly different in that there are no equations describing it (despite the claims of some comrades). If there were such an equation, it would be gone - like Winnie the Pooh's honey)
the weather was inspired by a good example on hubrahttps://habr.com/ru/post/495884/ yesterday
about a magic formula, well, as if only from the theory of games, you can look for something, the market can not be in memory, but it may depend on the previous move of other players
It's like in chess - learn someone else's game, then try to use it "head-on", everything goes according to plan, we beat them, but then for some reason the opponent did not want to follow our pre-learned plans
The weather was inspired by a good example on the hubrahttps://habr.com/ru/post/495884/ yesterday.
about a magic formula, well, as if only from the theory of games, you can look for something, the market can not be in memory, but it may depend on the previous move of other players
Well, it's like in chess - we take someone else's game, then try to apply it "head-on", it seems everything according to plan, we beat him, but then for some reason the opponent did not want to follow our pre-learned plans
Too difficult to screw up is also not very good, you may overplay yourself to the point of closing your positions or asking to add margin. It makes more sense to take your own risk, so that the potential was good in the total position of the cumulative. On all fronts.
?
Or to have a strong argument - the capital. And all can be taken out when necessary, and when they are not waiting).
I don't believe in algo success for some reason. Maybe if only to catch huge movements, automatically, when serious news, with long-lasting consequences... The robot reacts to powerful impulses... something like that.
And you can't always see everyone wanting to go in and out...) On the contrary, the very tinest is not visible...
Algo probably makes sense only if you're the fastest ... everything is imho ...
Man, I'm probably writing funny, but I'm trying to understand you, but I can't)) How can you automatically beat someone... You can't get in your head...) Every monitor on the look and do not guess who will press where and why, all this think over and make a decision with the preponderance in your favor ... BEFORE their move, but no...)