What You Need to Get Ahead Using E-Discovery Analytics

The challenge in e-discovery has been to develop technology that accurately collects, processes, searches and presents information. That goal has been largely accomplished. But in just the last few years, the information landscape has profoundly changed in both volume and diversity of data. Reliance on specialists to tame this data surge introduces risk and cost, but next generation e-discovery platforms make the power of analytics readily available to users who are not experts.

New terminology has surfaced as the techniques and tools of analytics have evolved. Predictive coding, technology-assisted review, continuous active learning and machine learning are just a few. One of the overlooked benefits of analytics is logical organization of a project. A helpful early approach is to limit data sets to only unique content. Three common forms of analysis are hash values, e-mail threading and textual near-duplicate identification.

Courts now embrace analytics and expect that technology will be applied to eliminate irrelevant or unnecessary data, and to make the review process more efficient and consistent. E-discovery software is evolving beyond technical capabilities and is now being designed around users — how they work, how matters are structured, how technology can simplify processes. It lets practitioners focus on the law instead of the technology. The e-discovery process now incorporates analytics at every stage to drive efficiency, cost savings and quality of results. This will move e-discovery out of the exclusive domain of experts and enable the concepts to become mainstream.