In describing predictive coding systems, it’s important to distinguish document-based systems from corpus-based systems. Document-based systems make their predictions based on the similarity of each document to a single, previously-categorized document. Corpus-based systems are, in addition, able to use higher-order properties of groups of previously-categorized documents to make their predictions. Because of this advantage, corpus-based systems are less affected by errors in coding individual documents. Continue reading
Group document reviews usually aren’t particularly ennobling. And in recent years we’ve learned that they can sometimes produce results that are worse than what we’d get from a well-trained machine.
That can change. We can use social technology to make group document reviews better, faster, and less costly, while making the reviewers’ work more professionally rewarding to them and more valuable to their employers. Continue reading
This article is about how H5‘s rules-based approach to technology-assisted review provides a great framework for illustrating cooperation in ediscovery. But first, some context.
By this time next year, Rule 1 of the Federal Rules of Civil Procedure will have been amended to codify the principles of proportionality and cooperation between opposing counsel. Continue reading