Hi Richard,
I'm not using python,
simply converted logistic regression (one of the learning algorithms for classification) in afl.
Hi Aron,
Congratulations! As usual your approach looks very concise and straight forward.
Can you explain the meaning of the target dataset?
I assume that the feature set you used is just C/REF(C, -1) - correct?
Can you describe the process/methodology you use to combine Amibroker and Python?
I work on the same approach and my process is as follows;
- use AB AFL for data mining and feature/target variables definition
- simulate the system in AB backtester
- run ML model in Python on CSV dataset from Amibroker
- create CSV tradelist (in Python) from OSS predictions
- AB backtester to obtain full trading stats (incl MC)
Is this similar to your approach or have you managed to integrate ML(Python) part in AFL?
Kind Regards
Richard
Posted by: Aron Pipa <aron@myafl.com>
| Reply via web post | • | Reply to sender | • | Reply to group | • | Start a New Topic | • | Messages in this topic (4) |
This group is for the discussion between users only.
This is *NOT* technical support channel.
TO GET TECHNICAL SUPPORT send an e-mail directly to
SUPPORT {at} amibroker.com
TO SUBMIT SUGGESTIONS please use FEEDBACK CENTER at
http://www.amibroker.com/feedback/
(submissions sent via other channels won't be considered)
For NEW RELEASE ANNOUNCEMENTS and other news always check DEVLOG:
http://www.amibroker.com/devlog/
EmoticonEmoticon