Machine learning in trading: theory, models, practice and algo-trading - page 333
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
RNN is probabilities, regression is on the input :)
Maybe I missed something. I'll read it again.
Yesterday I figured out what to do with neuronics. I decided to teach it to find the intersection of two MAs. The training sample is very easy to do. I will probably do it tomorrow. I will check its capabilities at the same time).
Maybe I missed something. I'll read it again.
Yesterday I figured out what to do with neuronics. I decided to teach it to find the intersection of two MAs. The training sample is very easy to do. I will probably do it tomorrow. I will check its capabilities at the same time).
Train at once in the corners of 2 or more regressions with different periods.) And it is necessary to make the NS vary the vector length for each regression, so it will adjust for loops and find them
Train at once in the corners of 2 or more regressions with different periods.)
MACs are for seeing possibilities, how many layers are needed, what data is sufficient, reaction to unnecessary extra data, to incomplete data, etc. Not for trading.
Something real will come later.
MACs are for seeing possibilities, how many layers are needed, what data is sufficient, reaction to unnecessary extra data, to incomplete data, etc. Not for trading.
Not for trading. Something real comes later.
If I were to apply MAs, not so.
You need to build three MAs separately twice and with different periods - by hawks, breaks, and opener and start crossing them....
It seems to me that this model will be more stable in real conditions.
I can't use this strategy without neuronics, most likely.
If I were to apply MAs, not so.
It is necessary to build three MAs separately twice and with different periods - by hawks, breaks, and open and start crossing them....
This is not a market analysis tool, it's just a beauty product... Think about the absurdity of the situation, you give just an average price for a certain period of time... for non-stationary BP... only on stationary BP they will have a prediction ability...
The MAs contain negligible amount of useful information, it's not a market analysis tool at all, but just for beauty... If you think about the absurdity of the situation, you just send average prices for some period... for non-stationary BP... only on stationary BP they will have a prediction ability...
MAs contain not a lot of useful information, it's not a tool for market analysis, but just for beauty...
If I were to apply the MA pins, not so.
It is necessary to build separately ...
This is not a tool for market analysis, but just for beauty. Well think about the absurdity of the situation, you send just averaged prices for some period... for non-stationary BP... only on stationary BP they have a prediction ability...
Added new features to the bot :D
Now I want to make the logic core a bit more complicated, add more inputs
On the graph half backtest, half forward :)
This is not a tool for market analysis, but just for beauty... Just think about the absurdity of the situation, you send just an average price for a certain period to VS... only on stationary VS they will have a prediction ability...
and i have the opposite opinion - that mashki is the only smart indicator that is really informative...and the only one that came to us from statistics along with stationary.
Poppies, or rather envelopes are an indispensable tool for measuring volatility...much better than a bollinger
IMHO
but you're a pro, you should know better....