IBM Watson Data & AI - Structured Ideas

This Ideas portal is being closed.  Please enter new idea at http://ibm.biz/IBMAnalyticsIdeasPortal

Automated Metadata Generation in WKC using Machine Learning

Providing the ability to provide an automated way to suggest Glossary terms (business terms) to data producers to link business metadata to columns is necessary.  For our Chief Data Governance organization, our mission is to link IBM business language to all columns ingested into our data lake.  As part of this mission we have built a tool/set of services that focus on assisting a Subject Matter Expert in linking metadata in an automated manner using Deep Learning algorithms as well as using NLC.   This product provides a set of recommended glossary terms that could be linked to a column or provides the ability to type on and search existing glossary terms as well as create new terms.  The power with this product is that it facilitates the process of linking metadata which can take on average of about a month and a half to complete, which has been reduced down to about a week for an SME.

  • Sonia Mezzetta
  • Dec 14 2018
  • Accepted
Why is it useful?
Who would benefit from this IDEA? As the Data Governance Product Owner within the Chief Data Office, I would like to migrate from IGC to WKC and manage all my business and technical metadata within our Cognitive Enterprise Data Platform and execute our CDO DG services using WKC so that I can provide the necessary functionalities for our data producers and data consumers.
How should it work?
Idea Priority High
Priority Justification
Customer Name
Submitting Organization Other
Submitter Tags
  • Attach files