Making predictive coding pay needs cooperation.

• Position: E-DISCOVERY

Recent legal decisions regarding e-discovery and electronically stored information (ESI) have shined a spotlight on predictive coding, which "is a type of machine-learning technology that enables a computer to help 'predict' how documents should be classified based on limited training provided by their human counterparts," according to Matthew Nelson, Symantec's e-discovery counsel.

It's a well-known fact that document review is one of the most time-consuming--and, therefore, costly--aspects of litigation. With the volumes of ESI multiplying exponentially, the more costly the old, manual methods of document review. Organizations and courts are looking to predictive coding to mitigate some of these costs.

If only it were that simple. "Despite judicial acceptance of predictive coding, the cost savings offered by the technology are quickly nullified when the parties cannot agree on its application," wrote James Freebery in an article on Inside Counsel.com.

The key to the predictive coding success in reducing discovery costs, Freebery stated, "hinges on the involvement of, and cooperation with plaintiffs' counsel."

U.S. Magistrate Judge Hanna Doherty (Western District of Louisiana) helped things along in the Case Management Order, In Re: Actos Pioglitazone Liability Litigation, entered in July. The order outlined the ESI protocol for discovery, including a detailed description of the predictive coding methodology the parties must use during discovery.

Since early 2012 there have been thee cases that have included unique...