Using Continuous Multimodal Learning to Reduce Attorney Review Costs

To support a litigation case involving a breach of contract, a client needed to deploy technology assisted review capabilities in order to meet a tight production deadline.

Challenges

Solution

Using Reveal's Brainspace technology, the leader in advanced eDiscovery data analytics, a small sample of 400 documents were reviewed and used to train a Continuous Multimodal Learning(CMML) model. CMML is an integrated set of features designed to support flexible interactive supervised learning workflows.

The Predictive Ranks from the CMML model were then used to prioritize review ensuring the most relevant documents were reviewed first. Additionally, Reveal's patented Diverse Active Learning was used to build a small training round from a widely diverse data set to ensure that no pockets of relevant documents had been missed.

Results

By using our Continuous Multimodal Learning, the client was able to reduce the review population to 70,0000 from 140,000, a 50% reduction in review volume. In addition, CMML produced an initial 75% richness level in a low richness data set.

With CMML, the client was able to find more relevant content faster, while reviewing far fewer documents. They were able to save approximately 1,750 hours of review time. By leveraging Reveal's Brainspace CMML, the client was able to meet the tight deadline – and save over $70,000 in attorney review fees on one case.

‍