Hi Gregg,
Thank you for your comprehensive reply. It looks like your approach is very different to waht I am doing but, your answers shed more light on the inner workings of ML approach.
I am probably more in line with the Pankaj statement - "never achieved accuracies of >70% in prediction, which result in a 40%-45% win-ratio in real life."
When I talk about traditional system development platform approach (like the one in Amibroker AFL) I mean for example using Bollinger Band strategy for Buy/Entry signal and for exit using Howard's approach
of "marking-to-market" daily. If one day ROC (for instance) is above your target you stay in the trade, if it is below you exit.
The same can be done in ML. Using Bollinger Band and price parameters as features one can use say DecissionTree model to predict next bar gain as a target.
Kind Regards
Posted by: richpach2@yahoo.com
| Reply via web post | • | Reply to sender | • | Reply to group | • | Start a New Topic | • | Messages in this topic (13) |
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