Progressive Casualty Insurance Company v. Delaney et al, Court Rejects Party’s Unilateral Decision to Employ Predictive Coding After Agreeing to Different ESI Protocol
This dispute is one of nine declaratory relief actions filed by Progressive Casualty Insurance Company in federal district courts concerning the takeover of failed banks by the FDIC (as receiver). The parties submitted a Joint Proposed ESI Protocol which was approved by the Court. Under the terms of the protocol. Progressive and the FDIC- R agreed to search terms which would be applied to ESI documents. Applying the search terms resulted in 1.8 million potentially responsive documents being culled to a 565,000 documents for review. Rather than producing the 565,000 documents, Progressive decided to utilize eight contract attorneys to manually review the ESI for relevance utilizing the on-line review tool, Relativity. After a month, Progressive determined it would take about 6-8 months at an unacceptably high expense to complete the manual review and began investigating an alternative approach.
Progressive retained an ESI discovery expert selected the Equivio Relevance Program and began using predictive coding techniques against the culled set of 565,000 documents without the agreement of the FDIC-R to ament the ESI protocol and without seeking leave of the court to amend the ESI order. The predictive coding software was run across the 560,000 documents culled from the keyword search process identifying 90,575 potentially responsive documents. While maintaining that predictive coding would achieve a much more accurate measure of relevant responsive documents, Progressive acknowledged that applying predictive coding on top of the search terms “is not always done.” Progressive applied a set of privilege filters to the 90, 575 documents identified by the predictive coding process and proposed to produce the 63,000 less likely to be privileged document without conducting further manual review. Documents that were more likely to be privileged would be put into Relativity for manual review and the privilege log would be generated utilizing Relativity. .
The FDIC-R opposed Progressive’s predictive coding proposal asserting that it was complicated and would lead to additional discovery disputes. The FDIC-R’s preference was for Progressive to produce the 565,000 culled from the 1.8 million data set using the parties agreed upon search terms with claw back provision for privileged documents. They argued that this approach would avoid further expense and delay associated with relevance review by Progressive’s counsel and shift the expense of the review to FDIC – R allowing discovery to proceed expeditiously. The FDIC–R further argued that Progressive sought to take unfair advantage of the agreement to compromise search terms by applying predictive coding to documents limited by the significantly narrowed keyword search terms. The FDIC-R suggested utilizing predictive coding to the 1.8 million data set as an alternative to Progressive’s proposal.
In its analysis, the Court noted that the stipulated ESI protocol provided that Progressive would produce documents on a rolling basis soon after the search terms were agreed upon and Progressive failed to do so. The FDIC-R filed a Motion to Compel production and in its opposition, Progressive informed the court of its new approach to ESI. Referencing Progressive’s e-discovery consultant, Conor Crowley, the court noted that many have persuasively argued that predictive coding has emerged as a far more accurate means of producing responsive ESI in discovery then manual human review or keyword searches. The court indicated that had the parties worked collaboratively and agreed on the onset to the use of predictive coding for ESI discovery, “the court would not have hesitated to approve a transparent mutually agreed upon ESI protocol.”
The Court emphasized that in the handful of cases that have approved technology assisted review of ESI, the courts have required the producing party to provide the requesting party with full disclose about the technology used, the process and the methodology. The court indicated that the use of predictive coding “requires an unprecedented degree of transparency and cooperation” between counsel in the review and production of ESI. The court characterized discovery in this case as “contentious” and noted that Progressive was unwilling to engage in the cooperation and transparency that its own expert explained was critical for predictive coding to be accepted by the court or opposing counsel. In granting the F Motion to Compel, found that approving Progressive’s predictive coding proposal or FDIC – R’s suggested predictive coding protocol would only result in more disputes and further day the completion of discovery.
Progressive Cas. Ins. Co. v. Delaney, No. 2:11-cv-00678-LRH-PAL, 2014 WL 2112927 (D. Nev. May 20, 2014)