Case Study: Major Bank achieves 98% responsive-document capture and 94% review-cost reduction with OpenText Insight Predict

Financial corporation gathers close to 98 percent of responsive documents, reduces review costs by 94 percent with OpenText Insight Predict

A major bank facing litigation needed to locate responsive documents for a production request but was left with over 2.1 million files to consider and lacked the time and budget to manually review them or confidence that keyword culling would be complete.

The bank and counsel deployed OpenText Insight Predict, a continuous active learning (CAL) technology-assisted review solution, seeding the model with prior tagged documents and using contextual-diversity batching and multimodal inputs to surface high-value items quickly. The workflow produced a defensible result—identifying about 98% of responsive documents (95% confidence, ±2% margin), cutting total review effort to roughly 6.5% of the collection and reducing review costs by 94%.