Machine learning for information governance

Content Analyst Company and Sherpa Software have formed a technology partnership that will bring machine learning capabilities to information governance initiatives.

The deal calls for Sherpa to license and embed Content Analyst’s CAAT machine learning-based analytics engine into the Sherpa Altitude IG software platform. The move will enable information governance (IG) professionals to apply IG practices, policies and business processes to electronic files and records based not only on the file attributes, but on the actual contents of the files as well, the companies say.

Sherpa is the first information governance solution provider to incorporate the CAAT technology. Sherpa will leverage the unassisted clustering capabilities of CAAT to automatically group conceptually related electronically stored information. Sherpa says CAAT will allow the Altitude IG platform to more easily identify ROT (redundant, outdated, trivial/transient content) for defensible deletion, and to identify corporate records needed for archiving according to the customer’s corporate records retention policies.