The quarterly publication of the International Legal Technology Association
Issue link: https://epubs.iltanet.org/i/67910
by Barry Murphy of EDJ Group In recent months, there has been no shortage of commentary around what technology-assisted review (TAR) means, how it is conducted and whether it provides faster, less-expensive review while using fewer people in favor of technology. By definition, as provided in the "Evaluation of Information Retrieval for E-Discovery," the TAR process involves the combination of people and computers to categorize documents in a collection as responsive to a production request, or those that should be withdrawn on the basis of privilege. Then, a person reviews and codes only those documents the computer identified as fitting either of these descriptions. Using the outcomes of this initial phase of human review, the computer then codes the remaining documents in the collection for responsiveness or privilege. On the contrary, the previously-held standard of manual review involved people to examine every document in the collection and then to code each as responsive or privileged — quite a time- consuming (and expensive) process. What does this apparent innovation in document review practices mean for organizations? Embrace TAR Simply put, law firms and corporate legal departments need to prepare for TAR in order to reduce e-discovery costs and improve the quality of review. The buzz around judicial rulings suh as those in the Da Silva Moore v. Publicis Groupe and B. Kleen Products, LLC v. Packaging Corporation of America cases have companies simultaneously interested in the potential judicial approval of various TAR techniques like predictive coding and nervous about challenges to the specific approaches and science behind TAR. Lost in the hype is the fact that TAR provides significant business benefits in the form of lower costs, better review accuracy and the ability to more quickly and efficiently make case strategy decisions. A recent in-depth study of this topic published in the Richmond Journal of Law & Technology concludes, "Technology- assisted review can (and does) yield more accurate results than exhaustive manual review, with much lower effort." The study takes into account the various "flavors" of TAR and reinforces there is no one-size-fits-all solution. Rather, the findings suggest an interactive 80 Peer to Peer