Predictive Coding: Will E-Discovery Swallow The Judicial System?

In an earlier article, we discussed the significance of Magistrate Judge Andrew J. Peck’s (SDNY) opinion in Da Silva Moore v. Publicis Groupe (2/24/12), a highly publicized decision that approved of the use of computer-assisted review in place of “eyes on” document review.

Eric Seggebruch, the Regional Manager for eDiscovery at Recommind, Inc., testified before Judge Peck as an expert witness during a  Da Silva Moore discovery hearing. Seggebruch has authored a helpful article titled “Electronic Discovery Utilizing Predictive Coding,” that provides both technical and practical insights concerning predictive coding and its likely future in the legal marketplace.  

At its heart, the ESI debate revolves around the discussion of the concept of proportionality. By way of example, Da Silva Moore is an employment discrimination case with a universe of some three million records subject to review for document production purposes. Proportionality asks the question whether the costs involved in identifying potentially relevant documents are justified by what is at issue in the underlying litigation.

Nearly one year after Judge Peck’s decision in Da Silva Moore, the attorneys in that case reportedly continue to submit extensive (and presumably costly) briefs on ESI discovery issues. It is for this reason that the title of this article asks whether e-discovery will swallow the judiciary. Leaving aside the staggering costs to parties in litigation, the judicial resources necessary to address these issues may not be up to the task considering the time and intensity with which these battles are fought.

In evaluating the efficacy of predictive coding, Seggebruch tells us that there are two critical terms of art – “recall” and “precision.” “Precision” asks how many documents one has to look at to find a relevant document. By way of example, if you review one hundred documents and find fifty relevant documents, you have achieved 50% precision. “Recall” may be the more important element of the two. If a search of one hundred documents brings back twenty-five relevant documents but twenty-five relevant documents are missed, then “recall” is only 50%. The rate of “recall” in any document production, whether predictive coding or “key word” searches are used, is critical to the integrity of the process.

With increased acceptance of predictive coding over time, it is likely that the “key word” paradigm, with which most lawyers and judges are familiar, will most likely change. According to Seggebruch, scientific studies have shown that “key word” document analyses are less efficacious than predictive coding. However, adversary counsel cannot complain about the level of “recall” obtained from the “key word” analysis performed if they had significant involvement in selecting the “key words” used in the search.

As an indication of how quickly the technology in this field is moving, in some cases, lawyers are now demanding ESI discovery “do overs.” These lawyers argue that when their adversary performed their initial ESI production early in the case, they were admittedly adhering to the then prevailing best technology. However, since that initial production, new ESI techniques, such as predictive coding, have become available to provide potentially  better results. To date, courts that have considered the “do over” petitions have either rejected them out of hand or required the requesting party to assume the costs.
 

ESI In New York State Court Practice

Are defendants in New York product liability and toxic tort litigation better off in federal court than in state court? Federal court discovery rules certainly are more liberal than state court discovery rules. There, plaintiff’s experts are subject to deposition and, if appropriate, Daubert challenges. In contrast, state court provides only minimal expert disclosure. However, state court rules concerning the production of electronically stored information (“ESI”) may be more favorable to corporate defendants litigating in state court. In state court, the general rule is that the requesting party pays for the defendant’s ESI retrieval. In federal court, the court will apply “proportionality” concepts, and balance the importance of the discovery with the burden on the producing party. Thus, the result of the burden shifting analysis is somewhat more complex and subject to more variables. As reported in this space on November 4, 2009, (“Cost Allocation of E-Discovery in NY Trial Courts”), the Joint Committee on Electronic Discovery, convened by the Association of the Bar of the City of New York, has recommended that the legislature amend the CPLR to address time-consuming ESI disclosure disputes. The new proposed CPLR rule is expected to address a litigant’s duty to preserve ESI in anticipation of litigation; the scope of that duty; and the scope of ESI production. 

An article in Kramer Levin’s Electronic Discovery Update (January 2010), “Cost Shifting in New York: Forum Makes All the Difference,” discusses the background of the general presumption in state court that the requesting party pays for the cost of discovery. Although the CPLR does not explicitly apply this presumption to ESI costs, New York state courts have followed this presumption when deciding how to allocate e-discovery costs. In Lipco Elec. Corp. v. ASG Consult. Corp., for example, the court found that “… cost shifting of electronic discovery is not an issue in New York, since the courts have held that, under the CPLR, the party seeking discovery should incur the costs.” Lipco Elec. Corp. v. ASG Consult. Corp., 4 Misc.3d 1019(A), 2004 WL 1949062 (Sup. Ct. Nassau Co. Aug 18, 2004). In contrast to state court practice, the standard under federal jurisprudence is less clear cut.  The Hon. Shira Scheindlin (SDNY) has articulated a multi-factored balancing test, which has been influential in guiding determinations of when the cost of producing “inaccessible” data should be shifted to the requesting party. Zubulake v. UBS Warburg LLC, 216 F.R.D. 280 (S.D.N.Y. 2003). The Kramer Levin Update observes that a recent New York trial court opinion declined to apply this federal approach, stating that it was “not empowered – by statute or case law – to overturn the well settled rule in New York state that the party seeking discovery bear the cost incurred in its production.” T.A. Ahern Contractors Corp. v. Dormitory Auth. of the State of N.Y., 2009 WL 806779 (Sup. Ct. N.Y. Co. Mar. 19, 2009). Citing the policy behind the rule, the court observed that the requester-pays standard gives a party “a strong incentive to formulate its discovery requests in a manner as minimally burdensome as possible.”  I predict that the differences between state and federal ESI practice will narrow in the near term, possibly with the promulgation of a CPLR rule, and that New York will ultimately adopt a more federal approach modeled on the influential Sedona Conference Working Group template.  However, for the present, a New York state court plaintiff runs the risk of incurring substantial costs in demanding burdensome ESI from a corporate defendant.  Be careful what you wish for!