Machine learning in trading: theory, models, practice and algo-trading - page 1774
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'll give you the simple answer - only specific skills are important in a relationship with a special
Well yes, I kind of try to zhimchat all of them in a special way, but the secret is what? :-)
in the moment ) catch it
in the moment ) catch it
Thanks Sensei.... I will know. Veronica, you're mine forever, though I doubt you read such forums, that's what's sad :-(
never say that out loud)))
never say that out loud)))
The FinR market is very sneaky! 8) This is both according to my observations and comes from his nature, by definition. This creature is very cunning and bloodthirsty, otherwise it would have been sucked out 8) In 2011 there was an article about Kohonen neural network on this forum. Taking that work as a base (https://www.mql5.com/ru/articles/283), then I started to whip up my modification. I wanted to set the task as follows: the NS collects a collection of patterns on the history (what kind of patterns? there were different variants). In working mode, the task of the NS is: to determine, identify fresh, incoming patterns. If there are similar patterns near us, the probability of a market bump increases. We work in the other direction. If the patterns are still repeating, the probability increases. If the estimated probability exceeds the threshold - we trade on the market "pattern destruction". I abandoned that work with NS (the project turned out to be quite time-consuming, and I abandoned it). Every normal person wants to stably earn. The trader wants the price moves in a monotonous way, drawing the shapes that he has recently seen (at least, subconsciously, he expects it). We want stability, repetition, and the financial market uses this natural (in this case) weakness. The market breaks patterns. If we've seen a trend, it's probably already over. And, the next time we expect the same reversal - but no way! It will give us something new. It's the same with the other "movement patterns" that we try to identify and trade. Have you ever noticed that? It seems to me that a trading system should predict what seems most unexpected to us at that moment. Predict the foul 8)
The idea is correct IMHO, at least it sounds logical, but how to check it?
Specifically "patterns" in the form of "shapes", there trivial"head shoulders", triangles, etc., have long disappointed me as candidates for patterns, the signs of which may determine the future price behavior, but some "conclusions" from the MO made on short sliding time windows, may well "oscillate", that is change the sign, on the forwards in the process of removal in time. Need to check it out, thanks!
Sometimes you read the posts and you realize. He is so fucking cute and attracted to the Ministry of the Interior. Well, fuck him ... as they say, to communicate with such ... That's just me... I woke up after Bucharest... And the main thing is that right away. No conclusions... Forget it, what's up with the quotes, we're in, so what...
don't be jealous, as they say, the right hand is the best girl, tired of the right hand you take the left hand
Greetings traders. I have a small question, but do not kick me, give me some advice. i know the direction of the pair movement for 5-10 years, i know the approximate movement structure in the form of a figure and how many points will pass in one direction, the question arises what should be introduced into the advisor, of course, to get a good profit, we have a direction, it remains to pick up or indicators and to build in the neural network, i.e. should i optimize an approximate price movement, and then run it, eventually i have to use 2-5 indicators or neuron. Next methods, a martin need or not, for me maybe 2 or 3 trades without oversized lot to open on the trend to correct and then closed. I would be grateful for advice. I will be grateful for the advice.
Stock up on Validol, good man.... )
There where it is necessary - iron concrete, and iron in it meteoritic, and concrete composite ;-) and it is also useful to sit on the bank of the river... or watch the fight from above...
From my experience:
- what to teach TC/NS plays a big role. For myself I am fully convinced that it is not money but stability (Lyapunov, Prigozhin);
- Robust results are more reliable when TS is optimized/learned/evolved as "closed" as possible, i.e. everything that will work in it in real life is already included.