Machine learning in trading: theory, models, practice and algo-trading - page 1528
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
These are all articles for morons. Those who are engaged in science - there is usually a lot of mathematics and there is almost no free access
Well, I think so, about options has already googled the material many times, or open advertising with science or like this ready option strategy with "smiles, strikes Put and Call", the same Wiki more information than in runet
the problem is where to get historical data, then develop a strategy and ... and how to test.... If you do not know where to get the historical data, then you should develop a strategy and test it at least once in a while, but if you do not know what platform they use, you may lose your time and money.
Well, that's about what I understood, I googled the stuff about options many times already, or open advertising with science or like this ready option strategy with "smiles, strikes, puts and calls", the same Wiki has more information than in runet
the problem is where to get historical data, then develop a strategy and ... and how to test.... for me it's not profitable if you sit on MT-terminals, it's too expensive - everything from scratch, you need to search on foreign forums, on which platform they use options
I wrote there above that it can also be applied to BP forecasting. But the volatility is always easier to predict than the initial BP, that's why they use options.
I wrote there above that it can be applied to BP forecasting as well. But volatility is always easier to predict than initial BP, that's why they sit on options
Well, we`ve been talking about Vols in PMs - there`s some repeats there, at least something happens regularly!
And as for predictions, I got "knocked out of my rut" by Savvateev. In his recent videos he openly said it's senseless to make predictions about BP.... he is a creep, he killed all my dreams! ))))
I wrote there above that it can be applied to BP forecasting as well. But volatility is always easier to predict than initial BP, that's why they sit on options
And how to predict volatility?
Well, about the ox we communicated in the PM - there are repetitions, at least something repeats regularly!
And about the forecasts, Savvateev "knocked me out of my rut", in his recent videos he openly said - it makes no sense to forecast BP.... he is a creep, he killed all my dreams! ))))
Yes, he has a competent series of videos on TI
And how to predict volatility?
I think only from the opposite - there was a surge of volatility, then there will not be for some time, but here the problem is reduced to determining the time to estimate the volatility surge, in fact, the TF, where we want to estimate a higher price speed than before this event (surge of volatility)
It's a bit more complicated than that... it's forecasted using Black-Scholes equation or stochastic equations like Merton jump, and MO is used to adjust the parameters. I don't know exactly how it is traded, but if there is a quality forecast, I think, it is not difficult.
All you need for opts is a forecast by will
Here's the stuff from the paid subscription. For me it is a bit complicated, as well as for anyone, I think :)
It's supposed to trade in the spirit of Markowitz's portfolio theory.
I agree completely, stochastic diffusers are a very complicated science. It's somewhat simplified because of:
1) Usually only linear stochastic diffusers are used, which are easy enough to understand if linear ordinary diffusers are understood.
2) Usually from linear stochastic diffusers go to regression.
Remember you wrote something about trees in games. Here's an article about it, I just came across it. It's actually an interesting algorithm, sort of.
https://medium.com/@pedrohbtp/ai-monte-carlo-tree-search-mcts-49607046b204
Remember you wrote something about trees in games. Here's an article about it, I just came across it. It's actually an interesting algorithm, sort of.
https://medium.com/@pedrohbtp/ai-monte-carlo-tree-search-mcts-49607046b204
I read on Habra that in cool games bot logic is not built on NS, but often on a decision tree, then I Googled, it turned out to be the algorithm of Rete ( Wiki )- the essence, it's a self-training system based on a knowledge base, CLIPS expert system is built on this algorithm - in the free access.
HH: I've downloaded a couple of books on CLIPS, I wish I had read all this stuff, it's just so much material and so frustrating )))) - It is easier to write a grid of orders, which is what I do))
I read on Habra that in cool games bot logic is not built on NS, but more often on a decision tree, then I googled, it turned out to be the algorithm of Rete ( Wiki )- the essence, it is self-training systems based on a knowledge base, the expert system CLIPS is built on this algorithm - freely available.
HH: I've downloaded a couple of books on CLIPS, I wish I had read all this stuff, it's just so much material and so frustrating )))) - It would be much easier to write a grid of orders, that's what I do )))
:D But these perversions don't really get me anywhere. Yesterday I read more about fuzzy time series, with examples on the sine wave