Interactive training of models is not supported in SQL Server Data Mining.
A workaround is available, in SQL Server 2008, for your problem: you can
create two mining models in the same mining structure and use data filters
for each mining model -- the first model filters by Age > 25, the second by
Age <= 25
--
--
--
This posting is provided "AS IS" with no warranties, and confers no rights.
Please do not send email directly to this alias. It is for newsgroup
purposes only.
thanks,
bogdan
"jennifer_chan" wrote in message
> Hi there,
>
> I'm fairly new to decision trees and have just got my head around using
> DMX
> and ADOMD.NET to create and process Analysis Services mining models using
> the
> Microsoft Decision Trees Algorithm. I am able to embed the resultant tree
> into my C#.NET windows form using the MiningModelViewerControl class.
>
> Is it possible to force a split on a node in the decision tree within the
> viewer? I cannot get this to happen in the viewer or via the code. Also i
> cannot see this being possible in SQL Server Management Studio.
>
> Forcing a split refers to specifying a variable or characteristic on which
> to
> further split a node (e.g age of customers > 25 years). It is expected
> that
> the node on which a split is forced, will get some child nodes as a
> result. I
> cannot add child nodes to any existing node in the code. And i cannot do
> anything in the Model Viewer. Any help i can get is greatly appreciated.
>
> Thank you!
>
>> Stay informed about: Forcing splits in a decision tree