Insight Predict is a second-generation TAR engine designed to help reduce review costs and time for outbound productions, deposition prep and early case assessment.
In July 2014, two of the leading experts in e-discovery, attorney Maura Grossman and professor Gordon Cormack, published research on the effectiveness of a new learning protocol for Technology Assisted Review called “Continuous Active Learning," or CAL for short. As shown in their research, CAL finds relevant documents faster and at lower cost than traditional TAR engines, speeding up review and cutting costs. It also simplifies the review process, solving the real-world problems that held back TAR from the beginning and making it effective in a much broader range of cases.
As the first commercial review product to use an advanced CAL protocol, Predict won recognition as “New Product of the Year” in the 2015 Legaltech News Innovation Awards. In 2017, the best got even better. Enhancements to the algorithm that powers Predict delivered increases of review efficiency of up to 40 percent. The updated algorithm expands Predict’s machine learning capabilities to include multi-word bigrams and trigrams, further improving Predict’s ability to differentiate relevant documents and prioritize them for review. For a set of 250,000 documents, that could mean savings of $50,000 to $100,000.
Despite best efforts from your review team, privileged documents may still slip through the cracks. TAR can help find them before they get loose.