Discussion of article "Random Forests Predict Trends" - page 7
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
... Rather than quibbling about econometrics....
is it true that the word "econometrics" was invented by economists who could not remember the words "probability theory" and "mathematical statistics"?
Yes. There are plenty of universities in the country that don't recognise the word"econometrics"
PS.
The random forests I'm discussing here refer to "machine learning", which in turn refers to artificial intelligence. That's to the point. For clarity of terminology.
But as they used to say in my youth, if we classify a chair and a table as furniture, science will not move one step forward.
Here comes the level of conversation. Overtraining is not a problem at all. That is, at ALL. it is easy to identify and easy to solve, without econometrics.
Can you give me a little hint as to how you determine overtraining?
But I'll have zero motivation unless the author shows some practical results of this model.
The point is not to get the grail, but to check whether your data set has predictive power or not. So it's just research, searching. And how else do you imagine the creation of TC? One and done?
In general, you have a wrong perception of everything. You want someone to hand you the right set of data on a platter.... Well, well, well.
And as for the fact that a person offers his services for money - do you think he should do it for free?
The point is not to get the grail, but to check whether your data set has predictive power or not. So it's just research, searching. And how else do you imagine the creation of TC? One and done?
In general, you have a wrong perception of everything. You want someone to hand you the right set of data on a platter.... Well, well, well.
And as for the fact that a person offers his services for money - do you think he should do it for free?
I give you the answer to your question - there is some "predictive power" in all data. So? All forex data has some sort of information in it.
Where is the money?
forward test - easy, simple and clear.
I give you the answer to your question - there is some "predictive power" in all data. So?
What makes you think that the temperature of your cat's arse has predictive power for the financial market? It may be a crude example, but the point is clear.
No, I don't - I don't have a cat and I doubt that the temperature of any pet is relevant to forex information.
By the way, I give 100% that the dynamics of the cat's temperature will have a non-zero correlation with the price series of a financial instrument
As for a person offering their services for money - do you think they should do it for free?
Not necessarily for a fee.
For the conclusion I need a csv-file with: date, quote + any number of preferably not redrawing indicators (you can and redrawing, but I will tell you how to prepare them), coded events such as the Fed, in general, whatever the author considers necessary. At least 20 such variables (predictors) to have something to discard, and over 10000 bars. I specifically, on figures show whether the specified set of predictors has a tendency to overtraining or not and from it is little probability of a fuck-up in the future.
If it all happens on this thread, it's free
If in private - 100 quid.
PS.
I have a dozen customers here. Before I started communicating with me, all were happy and cheerful, but now sad and thoughtful.