Machine learning in trading: theory, models, practice and algo-trading - page 1915
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
I've had a neural network that predicts the movement of four pairs for four months now. It is of higher quality than any indicator, I demonstrate it publicly. I can not give the link, otherwise the admin will be hysterical again because there are a couple of paid services. But in any case it is a real neural network and it really sees and predicts something.
a man who sells something and says that this particular chicken lays golden eggs for him - ............
Research and selling a product are incompatible?
And I already thought that this time no one would throw a stone at me)
Research and product sales are incompatible?
normal products do not even show
;)
There are neuronics and adaptive filtering and spectral analysis and Q-learning and clustering and training with a teacher, in which the teacher is himself, he himself pokes points on the graph where to enter and punishes the robot himself when he makes a mistake. The robot is adaptive, it acquires new knowledge and forgets old knowledge if necessary, so it is a beast.
What kind of network knows how to forget? What is the principle of forgetting?
What kind of network knows how to forget? On what principle does it forget?
I wrote that he has a huge number of algorithms in one robot, how do I know what network is there now, and whether it is responsible for memory at all.
Once used a SOINN network, also the principles of MSUA, but in what contexts it was used there, I do not know
https://habr.com/ru/post/192978/
)) I'm sure nobody here has even heard of it, and it's already 15 years old...
Without encroaching on your grail) there is a question - how does a neural network predict the bank's desire to buy or sell a certain volume (affecting the price) of currency (for example)? Any neuronet can only catch the inertia in the direction when speculative volumes are sold and the price actively starts moving. But a neuronet will never indicate exactly the moment of entering the participant who will change the price (price driver), although it is not needed - in 99% if you know how to identify the price driver and its direction your transactions will always be before the realization and you will have a stable profit. My company also has a department of algorithmic trading, but it is more focused on very fast scalping - the neural network also catches the inertia of the hft algorithms and based on its analysis our robots make deals by fully copying hft (only for certain markets and symbols). The basic trading is done by hand in the old way, since the price driver cannot be predicted (and there is no need to), you can only see it = the car will show you the turn signal before changing direction (you understand that the neural network cannot predict at what moment the turn signal of this or another car will turn on).
Have you heard of Maitreade? How much is he right? Thank you.
As you can see we can't divide by class, so either the target is crap or the signs, or all together)))
You are really good. The problem with most network developers is that they teach the network to predict price changes. You need to know who changes the price and how, and you have to teach the network to see who is going to change the price. If you give a network garbage to enter, you will also receive garbage. You do not need any indicators and other rubbish. Find someone who can tell you how to really gain a position for price changes, how the price behaves, how the mechanism of all this happens, teach the network to see these changes and the whole world is at your feet.
+1000% Very sensible thoughts.
You are really good. The problem with most network developers is that they teach the network to predict price changes. You need to know who changes the price and how, and you have to teach the network to see who is going to change the price. If you give a network garbage to enter, you will also receive garbage. You do not need any indicators and other rubbish. You need someone who will tell you how to really get a position for price changes, how the price behaves, how the mechanism of all this happens, teach the network to see these changes and the whole world is at your feet.
Ahhhhhh, I get your point...
Look, I'm sorry I snapped at you, but sometimes I'm not sure.
Here's my answer. He without conditionally infuriating one point, purely visual. But do not pay attention, because the main thing is the essence of the narrative, not how it looks and how creepy the sound can be... Just take note. yes I am and I think so. And yes I don't have 100% results, no more than 55% in the general sense of that understanding :-))))