DataScava and Business Intelligence

We commissioned a series of articles from Scott Spangler, former IBM Watson Health Researcher, Chief Data Scientist, and author of the book “Mining the Talk: Unlocking the Business Value in Unstructured Information,”  in which he discusses how and why DataScava’s patented precise approach to mining unstructured text data perfectly complements real-world big data applications in AI, LLMs, ML, RPA, BI, Research, Talent, and BAU applications. He also contrasts our Tailored Topics Taxonomies, Domain-Specific Language Processing, and Weighted Topic Scoring with standard approaches such as NLP.

DataScava represents a brand-new way of thinking about unstructured text data and Business Intelligence. It fits right into your existing BI toolset and takes very little training to get started. In “The Key Ingredients for Game-Changing BI from Unstructured Data,” Scott discusses:

• The importance of fully utilizing unstructured data in BI analytics.
• An overview of the most common current approaches to analyzing unstructured information in BI — Machine Learning, Generic Taxonomies, and Text Mining — highlighting the specific drawbacks of each.
• The importance of subject matter expert-driven taxonomies.
• How DataScava can be used to build and deploy these taxonomies at scale and mine unstructured data to maximize business value.

 

Our Approach

 

Domain-Specific Language Processing (DSLP)

 

 

Weighted Topic Scoring (WTS)

 

Tailored Topics Taxonomies (TTS)

 

Highlighter

 

 

Taxonomies for Financial and IT Domains

 

 

Taxonomies for Talent Mining and Skills Analytics