Robert Keeling, Esq., Co-Chair of the E-Discovery Group at Sidley Austin, offered advice to legal departments and law firms that aren’t getting the results they expect from predictive coding, in a recent edTalk sponsored by Exterro, Inc. and Georgetown Law CLE. Be selective during document collection. Use multiple models or techniques. Customize workflows. Be flexible. Adjusted parameters, algorithms, and even sample sets, especially in low-richness environments, can yield better results; and tactics like seeding the sample with responsive documents can help train the algorithm.
Heidi Gardner, Ph.D., Lecturer on Law at Harvard Law School, says that debunking myths about collaboration is often the first step in helping lawyers see the real benefits. Gardner discovered that revenue grows exponentially when practice groups work collaboratively with a given client. The benefits of collaboration don’t just accrue to organizations; professionals who collaborate build networks of colleagues.
The 2015 amendments to the Federal Rules of Civil Procedure focused on the need to resolve civil disputes in a “just, speedy, and inexpensive” way. Hon. David Waxse, United States Magistrate Judge in the District of Kansas, identifies the concept of proportionality as a key means of achieving those goals. There are things that can be done at each stage of e-discovery to deal with proportionality. Limit document retention. Use technology for review. Limit the scope and format of production. Tactical gains from disputes over document production rarely outweigh their negative impact on the cost and speed of litigation.