Streamlining Document Review for DOJ Antitrust Division Compliance

Uncertainty on How to Proceed Effectively, Timely, and Defensibly with 70M Documents to Review

A Fortune 500 health insurance provider was facing a fast-approaching deadline set by the DOJ Antitrust Division for producing documents related to a planned upcoming high-stakes merger. To comply with the DOJ’s request, over 31.5TB of data from 137 custodians and 170 separate media sources needed to be collected, processed, filtered, and reviewed. Sources included: legacy email databases, SharePoint repositories, shared and personal network drives, laptop/hard drives, and hard copy documents. It was unclear to the health insurance provider how to proceed with this massive review of 70M documents in the most effective, timely, and defensible manner.

Significant Reduction Out the Gate Using Lighthouse Structured Analytics

Using Lighthouse deduplication and filtering, the processed data set was substantially culled down from 70M documents to 21M, a 70% reduction. In parallel to these data reduction efforts and in preparation for the next phase of work, Lighthouse TAR experts created a TAR protocol and production schedule.

Precision and Speed: Reviewing 21M Documents in 3 months

Using the TAR protocol, the team achieved a high-precision, high-recall output across the range of diverse data in the review set. The entire review of 21M documents was completed with three months, resulting in 5M responsive documents produced to regulators.

Lighthouse’s expert handling of massive data volumes through analytics and technology-enabled review protocols enabled the Fortune 500 health insurance provider to meet stringent DOJ deadlines efficiently, ensuring compliance and readiness for their high-stakes merger.