Machine learning in trading: theory, models, practice and algo-trading - page 2924
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
Doesn't look bad if it's a full auto.
Does it look bad if it's not full automatic?
That's trading on the news - I don't do that.
Earlier you wrote:
"
If we look at the chart with trades, we can see that the erroneous predictions fall on strong market movements, i.e. the model for some reason erroneously predicts the directions of strong market movements. Thereasons are not clear, as the model itself is trained on the sample obtained from Sample.
"
So, now you understand - it's the news, the consequences of which you do not want to predict?
I am able to predict about 40% of correctly positive examples, and there are 20% of them in the sample. If that's the problem you have, then there will be two models working just fine. I have the classification almost on the daily ATR 61.8 at the moment of crossing ATR 23.6.
and if it's not full, it doesn't look good?
Value judgements are hard to evaluate then :)
Well, maybe he will - who knows.
I was surprised by another thing - the function is very similar to the Head and Shoulders figure - and got curious:
1. Is it possible to find a formula-constant for any other patterns.
2. How to estimate the plausibility of the bar formation and the formula.
Weierstrass's f-ia is the very first fractal. Dmitrievsky was working on fractals about 10 years ago on fartlabik, ask him when they will be released.
SME is just beautiful.
unlike other half-baked exchanges.
I recommend it!
//not for beginners of courseThe TS is built on predicting the next bar on R and then using this prediction in an Expert Advisor on MKL4.
Model on R.
It works on H1, the teacher is trending (ZZ), predicts the next bar. OutOfSampe is not used as the model is recalculated on each bar.
Efficiency of predicting the next bar 78-80%
Positive prediction performance on one of the next 8 bars is over 95%.
The model is excellent.
BUT.
It is impossible to build a workable TS on this model. We get about 78% of profitable trades, but they are small. But the losses are much larger.
In the Expert Advisor itself we cut losses and let profits grow. This leads to the fact that the number of profitable trades decreases with simultaneous growth of a profitable trade and reduction of a losing one. But it still does not solve the problem.
Here is one of the many results of the exercise with TR and SL.
If we look at the chart with trades, we can see that the erroneous predictions fall on strong market movements, i.e. the model for some reason erroneously predicts the directions of strong market movements. The reasons are not clear, as the model itself is trained on the sample obtained by Sample.
Typical chart.
It is hard to see, I have highlighted deals with vertical lines
In a few more years, you'll get to spectral analysis.
At random is not interesting, on this data to arrange a competition for a few people would still be an incentive.
as long as the market for you time series, there will be no achievements, and if there are, it is a fitting on the history....
Limit entry?
No