Ten predictive coding concepts
Predictive coding has become a buzzword in e-discovery, but when it comes to taking a close look at implementing e-discovery processes, it can become a daunting topic to tackle. Edward Sohn, assistant vice president of litigation solutions for Pangea3, recently shared ten predictive coding concepts with the Association of Corporate Counsel (ACC). These top concepts are important to anyone who wants to become oriented to the presence of predictive coding in today’s litigation solutions, or simply know the vernacular before reading the next e-discovery article.
In addition to clarifying exactly what technology-assisted review and predictive coding are, these concepts help to explain how predictive coding works, as well as important characteristics and the essential points to remember when using predictive coding.
For example, Sohn addresses the defensibility of predictive coding as an approach to e-discovery and provides tips on how to ensure the establishment of a highly defensible predictive process – in the face of severe sanctions for discovery misconduct. Statistical legitimacy is also discussed; as Sohn explains, samples are used as metrics to measure the machine’s predictive ability by two metrics: precision and recall.
To learn more about what predictive coding is, how it works, and how to most effectively use it in a litigation strategy, find the article in ACC’s online Legal Resources.