Machine learning in trading: theory, models, practice and algo-trading - page 1999
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
Don't laugh, but get into it...
You don't need a code, you need log rules (this is a model), take these rules and paste them into your code, the sum of the predictions of the rules will be the answer of the model - "1" or "-1"
If you don't understand it then ask
while I am good ))Please don't tell me what's wrong...
As I understand it, I take the previous 10 values and go through the sliding window, if the condition at the step satisfies, for example
condition "X[,1]==X[,1]" then I add to the prediction pred [18,] "1" and so on.
p/s (added) although I misunderstood something...
Are these coefficients after training? If the characteristic of the series changes (there will be other numbers) , then we have to retrain.
As I understand it, I take and pass through the sliding window on the previous 10 values, if the condition on the step satisfies, e.g.
condition "X[,1]==X[,1]" then I add to the pred prediction [18,] "1" and so on.
Yes, exactly like that...
You should only take into account that X[10] is the last candle in my case and in your mt4 it will be X[1].
condition - are these the coefficients after the training?
Condition are rules, normal log rules, which are the result of training...
If the characteristics of the series change (the numbers are different), then you need to retrain.
Well, another training on other data (characteristics)== other rules (other numbers)
Just make him a model in the form of logging rules, let him embed it in his code, why torture the man with python?
Or should I do it?
Only take into account that X[10] is the last candle in my case and in your mt4 it seems that the last candle is X[1].
My data is in an array. Here are the last 21 candlesticks. at the top of it is the last current value I want to predict. i.e. i need to start from 0.0925306577 .
Show me an example for the first two data, at least.
Do what you want) I just restarted the bot, it's testing again
Max, make this damn bible)). 10 minutes of time, and we'll fiddle with it!
Max, make this damn bible))) 10 minutes of time, and we'll be picking!
I have data in an array. Here are the last 21 pieces. At the top there is the last current value, which I want to predict. That is to start counting from 0.0925306577 .
If you want just to check the prediction, yes
Well, can't you just copy the code into one file?)
are you sure you know how to make libraries?
Are you sure you know how to make libraries?
Where are X[,3], etc.? Or don't need them? I don't understand X[,1] == X[,1] meaning? You have to go through the last 10 values to predict, or 10 times with a shift of 1 over 10 values?