RenewData® Announces Enhancements to its Language-Based Analytics℠ Offering

Global News

19
Aug
2013

Editor

New Dashboard Increases Transparency and Predictability of eDiscovery Review

RenewData, a full-service eDiscovery provider that offers the industry’s most advanced spectrum of review acceleration solutions, today announced enhancements to its Language-Based Analytics offering. The powerful document review accelerator, which integrates with kCura’s Relativity, offers significant time and cost savings along with transparency and predictability with eDiscovery review projects.

The new features include a Dashboard that offers:

• Real-time reporting on the review status of projects that helps you determine how many reviewers and how much time it will take to complete the review.
• An acceleration rate that displays the ratio of documents reviewed to documents tagged and represents the leverage gained by use of Language-Based Analytics.
• Intelligence on relevant language so you understand what reviewers are finding in the document collection.
• A summary view of key metrics including document coding, batching, highlighting and progress.

Each reporting component consists of a widget that provides a real-time, graphical overview of key metrics for a case. The Dashboard is designed to allow for additional measurements and widgets that will be released in the coming months.

“Oftentimes, counsel has no clear, real-time insight into the important aspects of document review,” stated Andy Kraftsow, chief scientist for RenewData. “The Language-Based Analytics Dashboard provides the needed metrics that help them understand where they are, what’s trending and what needs immediate attention.” 

The Language-Based Analytics Dashboard helps you manage progress towards a lean, more efficient document review process – leading to valuable cost savings. With Language-Based Analytics, first-pass review is typically completed before 20 percent of the collection has been reviewed. Its patented highlight-driven bulk tagger saves significant amounts of money by assuring that relevant language is coded consistently and enabling the review of only one copy of the highlighted language instead of dozens of copies. Language-Based Analytics also offers a randomizing “Next-Document” algorithm that accelerates the appearance of relevant documents and helps assure that all relevant language and the documents that contain that language will surface before 20 percent of the collection has been read.