Text Extraction used to predict Resolving Method

I have a problem and I'm not sure how to approach it. I have a bunch of resolved cases, with the original problem description, and an identifier that points to the method used to resolve the case. I'd like to use Term Extraction on these resolved cases to relate the terms used in the original problem descriptions to the resolving method. So I'm thinking that the data modeling structure would consist of a case with the resolving method and a nested table of all the related terms. However, what I want to do is then take a new problem description, extract all the terms for the description of the problem description, and then use these terms to predict what the resolving method would be. What's the best approach to do so? Could I use Microsoft Association Rules to do so? Or could I use Clustering? I'm pretty much a newbie when it comes to Data Mining.

July 22nd, 2015 11:11pm

Hi Martin,

I am trying to involve someone more familiar with this topic for a further look at this issue. Sometime delay might be expected from the job transferring. Your patience is greatly appreciated.

Thank you for your understanding and support.

Regards,
Katherine

Free Windows Admin Tool Kit Click here and download it now
July 26th, 2015 9:48pm

It looks more like a "Machine Learning" question than data mining. I suggest that you check http://studio.azurelm.net to do some experiment. You can use the text analytics web service from Azure Marketplace to extract key phrases, and use feature hashing to turn key phrases into feature columns, and then choose different classifiers to predict the "resolving method" labels. You can easily use score and evaluation modules to identify which algorithm is the better approach.
July 28th, 2015 12:15am

This topic is archived. No further replies will be accepted.

Other recent topics Other recent topics