TAR for Smart People Outline - Chapter 13


Here's another installment in my outline of John Tredennick's 'TAR for Smart People'. I last posted an installment on February 10, 2017. This night's installment is on Chapter 13, "Case Study: Using Insight Predict for Review of Rolling Opposing Party Productions Insight Predict Finds 75% of Hot Docs While Cutting Review 92%".

The challenge in the case study involved finding hot documents in a production received from an opposing party in several different installments without having to review them manually. Catalyst touts its Insight Predict system for its ability to use continuous active learning to re-rank every document as new documents are added, and deal with productions that have a small percentage of relevant documents. Attorneys reviewed documents in small batches of 20 which were then fed back into the system to re-rank documents dozens of times each day. The system enhanced the percentage of relevant documents in the attorney batches from 1% to 7%. The majority of key documents in the production were found after only 8& of the production was reviewed.

Catalyst's system also used contextual diversity sampling to find pockets of documents that are unlike those the attorneys have already reviewed.


Contact Me With Your Litigation Support Questions:

seankevinoshea@hotmail.com

  • Twitter Long Shadow

© 2015 by Sean O'Shea . Proudly created with Wix.com