An AmLaw 100 law firm, representing a global entertainment company that received a Second Request from the U.S. Department of Justice (DOJ) in connection with a proposed $60 billion acquisition, had been given 60 days to analyze, review and produce responsive material from a 30 Terabyte document collection.
The law firm hired a litigation service provider (LSP) who worked closely with the U.S. Department of Justice’s (DOJ) Antitrust Division to determine the parameters and protocols for the use of technology assisted review, as well as the requirements for final production specifications.
Using our industry leading supervised learning technology, the LSP deployed Reveal's Brainspace Intelligent Coding workflow which leverages logistic regression to provide the most accurate predictive ranks for auto coding documents. A small sample which included 5,040 control documents and an additional 1,750 training documents were reviewed by a subject matter expert.
It was determined that Brainspace’s Intelligent Coding required, on average, 40% to 50% fewer training documents to train a classifier versus other supervised learning platforms in the market.
The completion of the 2nd Request would not have been possible in the time provided without Reveal's supervised learning capabilities. The LSP was able to achieve the agreed upon recall and precision rates while auto coding approximately 85% of the document review population.
After reviewing a statistically valid random sample of the non-responsive documents, the DOJ agreed that their demands had been met. Leveraging Reveal's Brainspace technology, the client was able successfully meet the 60 day deadline while producing just under 222,000 documents to the U.S. Department of Justice.