Generic Machine Learning Solutions for E-Discovery

In predictive coding the team has developed generic models for relevance and privilege that can be moved from production to production though use of dynamic feature development. In document classification we have a library of over 100 document type models that are automatically run and auto coded for any production. In unitization our solution works on any set of images that do not have any document boundaries. This article briefly describes the specifics of document classification and unitization in the ongoing e-discovery process in In re Methyl Tertiary Butyl Ether (MTBE) Products Liability Litigation, Unitization The team received over 4,000 scanned claim files from the Pennsylvania Underground Storage Tank Indemnification Fund (USTIF). All or most claims had at least one large backscan folder that contained the early filings in each…

Link to Full Article: Generic Machine Learning Solutions for E-Discovery

Pin It on Pinterest

Share This

Join Our Newsletter

Sign up to our mailing list to receive the latest news and updates about and the Informed.AI Network of AI related websites which includes Events.AI, Neurons.AI, Awards.AI, and Vocation.AI

You have Successfully Subscribed!