PREDICTIVE CODING

Predictive coding is a combination of machine-learning technology and work flow processes that use keyword search, filtering and sampling to automate portions of an e-discovery document review.

The goal of predictive coding is to reduce the number of irrelevant and non-responsive documents that need to be reviewed manually. The computer program identifies document properties and refines search parameters according to rules created by humans.

For example, in a legal context, predictive coding software uses a mathematical model to scan electronically stored information and locate data most relative to a case and coding means to digitally categorize a document as being responsive or unresponsive. The technology uses a computer-categorized review application to classify documents according to how well they match key concepts and terms in sample documents created by a legal team. After the program identifies relevant documents according to the key concepts and terms, a legal team reviews the documents.

Proponents of predictive coding say it saves time and money because, instead of examining a huge set of electronic files and records manually, the technology allows a much smaller portion of data to be reviewed manually.