DSi One of First eDiscovery Firms to Use Predictive Coding Tool “Zoom”

Share Article

DSi, formally Document Solutions, Inc., proves technology-assisted review techniques can be used on smaller cases to streamline eDiscovery, slash review costs

News Image
We ended up saving our client about 640 hours of manual review, which equates to at least $176,000 in savings if you assume $275 an hour for review.

Harnessing today’s leading technology to optimize eDiscovery for clients, DSi’s latest eDiscovery project has helped it become one of the first firms in the industry to use Equivio’s Zoom predictive technology inside the Catalyst platform.

It’s a project of many firsts for DSi, as this project also marks the smallest case, based on data collection size, on which DSi has performed predictive coding.

DSi Senior eDiscovery Consultant Jeff Stoneking says the project proves predictive coding tools “don’t have to be the heavy artillery only brought out in giant cases, but are tools that can be applied to smaller scale projects to yield the same significant cost reductions. Clients shouldn’t fear the power of predictive coding or eliminate it as an option if they have a case that involves a small amount of documents, such as 50,000.”

DSi’s project involved 160 GB of data (about 640,000 documents) collected from four custodians. After date filtering and deduplication, which reduced the data set by 93 percent to 12 GB (about 50,000 documents), the files were loaded into Zoom. Attorneys performed a first pass review of 1,600 documents, a statistically valid sample of the data population, to “train” Zoom to recognize and code documents accurately. Zoom then applied this knowledge to the entire universe of document to identify, prioritize and weigh documents based on similarity.

Based on the richness of the data set and the associated feedback from the predictive engine, the TAR platform determined approximately 18,000 documents likely to be relevant. The predictive technology indicated that the majority of relevant information would exist inside those documents, moving them on to a ‘second pass’ review. In total, Zoom eliminated 32,000 documents from the client’s review process.

To further ensure that the elimination process was sound, DSi’s quality control procedures included the additional step of having attorneys sample and test what was eliminated to verify the low richness rate (‘test the rest’). This validation step ensured the predictive technology had correctly separated the relevant information from the rest.

“Going into this case, we knew that leveraging predictive coding technology would make better use of our client’s internal resources and significantly control discovery costs,” said Stoneking. “We ended up saving our client about 640 hours of manual review, which equates to at least $176,000 in savings if you assume $275 an hour for review.”

“With document-by-document review becoming physically and financially unfeasible, we’ve known that there will be an even greater reliance on technology to analyze data in the future,” said John Burchfield, vice president of business development. “Our technology-assisted review techniques, which include predictive coding, are optimizing the review process, providing more accurate review results and giving clients a better understanding of their data. We look forward to the future of eDiscovery and embracing the technological advancements along the way.”

To learn more about DSi and additional eDiscovery success stories, visit http://www.dsicovery.com

About DSi
Serving law firms and corporate legal departments global wide, DSi (formally Document Solutions, Inc.) is a litigation support services company that provides a wide variety of eDiscovery and digital forensics services. Through five core business processes—DSicollect, DSintake, DSinsight, DSireview, DSisupport—DSi’s highly trained staff will help you harness today’s most forward technology to gain a competitive advantage. DSi is headquartered in Nashville, Tenn. and also has offices in Knoxville, Tenn., Cincinnati, Ohio, Charlotte, N.C., Houston, Texas and Minneapolis, Minn.

Share article on social media or email:

View article via:

Pdf Print

Contact Author

Jeff Bradford
The Bradford Group
615-515-4888
Email >
Follow us on
Visit website