What is the perspective in your opinion? - page 2
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
Excuse me, what is NS?
TUT
Here
Those who know the formula do not need NS.
Why so cynical =)
Then we have to admit that "Grail" is far from an ideal term for successful trading ;)
TUT
TUTHere
In my view, it is about patterns. It doesn't really matter how you look for them, with or without neural networks or cluster indicators.
The promise, in my opinion, is in the patterns.
Of course in the patterns, if you're an idealist - you could say there's no other way)
How they are searched, with or without neural networks or cluster indicators, does not really matter.
Something tells me it doesn't really =)
NS searching for patterns or filtering signals with conventional TS. I don't believe in prediction, you cannot know the future and you cannot extrapolate it either, because there is NO FUTURE! But classification is another matter - there is a certain output (pattern/conformity) and there are characteristics of this output (parameters of something/inputs), a very good example of classification - Fisher's Iris (types and parameters of types) -> define type, by its parameters, which IMHO fit the market (reversals, trend, etc. or signal filtering by TS), there is a profitable signal with a set of characteristics and loss signal with a set of characteristics, divide the wheat from the chaff)
The second variant(again IMHO) Total diversification - 3 TS - trend, counter, bezindikatornaya, working either in triple or by changing each other, for example a drawdown balance + a few currency pairs, but initially the tactics for the 3 TS should at least be zero, ie do not plummet - this approach is similar to a portfolio of securities, but instead of diversification by different securities, there are several tactics and several currencies.
Option 3 - manual trading + development of market vision (intuition, after all, the best NS is in the head, it's called - Brainwave).
NS searching for patterns or filtering signals with conventional TS. I don't believe in prediction, you cannot know the future and you cannot extrapolate it either, because there is NO FUTURE! But classification is another matter - there is a certain output (pattern/conformity) and there are characteristics of this output (parameters of something/inputs), a very good example of classification - Fisher's Iris (types and parameters of types) ->Find type, by its parameters, IMHO suitable for the market (reversals. trend, etc. or signal filtering TS), there is a profitable signal with a set of characteristics and loss signal with a set of characteristics, divide the wheat from the chaff)
I agree, we need to make a hierarchical neural network for that.
I agree, it is necessary to make a neural network hierarchically.)
I agree, you need to do the neural network hierarchically for this.