Large Global Law Firm (unnamed)

In a civil litigation matter, the firm collected and processed over 1 million documents on behalf of the defendant. Opposing counsel insisted on a broad keyword search list that would result in a tenfold increase in documents requiring review—nearly 200,000 documents—dramatically inflating the defendant's costs. The firm had little experience with predictive coding and needed expert guidance to propose and negotiate an alternative approach.

The firm engaged Consilio to implement a predictive coding workflow targeting 90% ±5% recall. Consilio guided a four-round iterative training process: an initial random sample of 2,057 documents immediately set aside 162,000 as non-responsive; subsequent rounds refined the model using biased draws, additional random samples, and a disagreement-reversal technique. A parallel workstream was added so junior attorneys could begin second-level review of high-probability responsive documents concurrently.

Predictive coding eliminated 89% of the original 200,000-document corpus from consideration, reducing the final review pool to approximately 21,500 documents while achieving the 90% ±5% recall target. The client saved at least $209,000 in first-level review costs (at a typical per-document review rate) and avoided days or weeks of unnecessary review time. The approach also enabled the client to produce documents one day sooner than would otherwise have been possible.

• Expert guidance on predictive coding protocols is critical: without it, parties risk either failing to reach agreement or implementing an unworkable workflow that leads to disputes and sanctions.
• Human coding inconsistencies (e.g., coding document families without per-document review) can significantly impair model training and must be caught early via QA.
• A disagreement-reversal round—where the model's probability scores conflict most sharply with human coding—can surface and correct reviewer errors that marginal training rounds cannot resolve.