It is safe to assume that at this point most litigators are familiar with the term predictive coding. It is touted as a cure for most of what ails the discovery process and excoriated as a symptom of legal commoditization. The truth is probably somewhere in the middle. When used under the right circumstances, it can genuinely improve the quality of document review and significantly reduce costs. To realize those benefits, however, it is important to understand what predictive coding can and cannot achieve, and to understand when and how to use it in any particular case.
Broadly speaking, predictive coding automates the document review process. It uses technology to identify relevant documents in order to reduce the volume of data that needs to go through costly and time-consuming manual review. Presently, this automation is only partial. Some manual human review is still needed, and the mathematical algorithms powering predictive coding must be tested and verified through data sampling. Further, the use of predictive coding is not and cannot be used as a substitute for judgment. We may get to pure computer review someday, but for now, it is still computer-assisted review. For now, knowledgeable people control the technology and are the key to a successful outcome.
