Technology-Assisted Review (hereinafter TAR) is broadly defined as the use of computer tools to determine the relevance of selected documents to any issues in a given controversy. The most utilized form of TAR, known as predictive coding, allows a human reviewer to utilize a select sample of documents to “train” a computer to recognize patterns of relevance in the universe of documents under review.

To be more precise, the parties input foreseeably relevant criteria into the coding software, such as keywords, dates, names of individuals, and document types. As the coding software applies this human “training” in an iterative fashion, a smaller relevant subset and a larger set of irrelevant documents is produced. Because predictive coding produces a smaller, more accurate set of relevant documents, the producing party spends less time and cost on reviewing for privilege, and the requesting party similarly expends fewer resources on determining the accuracy of the information than had it applied manual document review and keyword searches.

The use of TAR was first sanctioned in an opinion issued by Magistrate Judge Andrew Peck in Da Silva Moore v. Publicis Groupe, 287 F.R.D. 182 (S.D.N.Y. 2012). In citing to his own law review article, Judge Peck held in this opinion, now-considered seminal in e-discovery law, that the expediencies and cost-savings intrinsic to TAR should be recognized as a permissible way to search for relevant electronically stored information. Peck went beyond merely giving the imprimatur of validity to predictive coding and TAR writ large. Rather, he issued a call of arms of sorts and formally instructed the Bar to take away from his opinion that TAR is the wave of the future and should be seriously considered whenever feasible, particularly in discovery proceedings that involve “large-data volume cases.”