On February 8, 2012, Magistrate Judge Andrew J. Peck heard arguments in Da Silva Moore v. Publicis Groupe, No. 11-CV-1279 (S.D.N.Y.) addressing the use of predictive coding as an alternative to an eyes-on review of millions of documents. To utilize predictive coding, an attorney must manually review a small subset of the total amount of documents that are potentially involved in the litigation. As the attorney codes or “tags” documents as relevant, the predictive coding software is “trained” as to the characteristics that make a document relevant and, at the end of that review, the software is fully “trained” to predict how the attorney will tag documents and able to review and tag the entire set of documents itself.
At the February 8 hearing in Da Silva, Judge Peck discussed the review of 2.5 million documents. It was agreed that 2,399 documents would be manually reviewed for relevance and that the use of predictive coding remained subject to court approval. The parties were asked to submit an E-Discovery protocol, which will include predictive coding, as early as Thursday, February 16, 2012. Given Judge Peck’s statement: “[t]his may be for the benefit of the greater bar, but I may wind up issuing an opinion on some of what we did today,” we expect to see an opinion addressing predictive coding in the near future. This opinion is likely to be one of the first addressing this topic. Stay tuned to ediscoverylawreview.com for further details and analysis of this emerging issue.