Machine learning in trading: theory, models, practice and algo-trading - page 1210
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
Well, it's ok, so maybe it's better to go straight to python or r... so that you can use MO without any hassle
And nowadays you can't get anywhere without MO when ships sail the universe...
You can't get out of Sharp to Python. There are special versions of Python with Sharpies but it is not a fact that they support all Python packages.
VS 2017 out of the box.
Question about packages. It is not yet certain that MS Python with Sharp supports everything. I won't assert it, but there are rumors that it does.
The preliminary results (since I haven't made all predictors yet) on creating a model that determines profitable models (1) were not so bad, here is the breakdown by y - profit on the independent sample, and by x - 1 - TP+FP, and 0 - TN+FN.
The target was profit of 2000, well it hasn't been achieved so far, but only 3 models out of 960 have entered the loss area, which is not a bad achievement.
The table of conjugacy
The average unclassified financial result is 1318.83, after classification 1 - 2221.04 and 0 - 1188.66, so the average financial result of the models has increased by 68%, which is not bad.
However, whether this model can work with models built on other data remains to be seen.
Logloss training - surprisingly, the test sample (on which the model is automatically selected - not the training sample) and the independent (examination) Logloss_e almost perfectly converge.
So does Recall.
And the indicator Precision surprised me, since by default I usually use it to select the model, I had no training because it immediately equaled 1 on the first tree.
And the different metrics on the test and exam - the result surprises me a lot - a very small delta.
From the graphs, of course, you can see that the model is over-trained and could have stopped training at 3500 trees, or even earlier, but I was not engaged in adjusting the model and the data is actually with the default settings.
Esteemed forum members, could you please tell me, because I'm too lazy to read 1200 pages, has anyone here tried to implement machine learning based on results of trading on closed EAs?
The answer: if one loses, the other takes, it is clear without MO.
Dear forum users, could you please tell me, because I am too lazy to read 1200 pages, has anyone here tried to implement machine learning based on results of trading on closed EAs?
I don't think so, usually if someone is seriously engaged in such cases, he/she has a separate web site to maintain his/her creation, or does it for personal use
In the past NeuroShell DayTrader could make a trained NS out of everything you gave it (in your case your trading history), then the whole project died out, now I don't know, I haven't seen anything like that
It is unlikely, usually if someone is doing something like this seriously, he or she has a separate website to support his or her creation, or does it for personal use
NeuroShell DayTrader used to be able to make a trained NS from everything you gave it (your trading history), then the whole project stopped, now I don't know, I haven't seen anything like that