Technology Assisted Review
Surface relevant content faster and reduce data.
TLS's discovery consultants are highly experienced project managers and former litigators who expertly develop workflows implementing machine learning technology. Our Technology Assisted Review (TAR) technology helps you meet stringent deadlines while saving you significant time and reduce overall spend in the document review process.
Technology Assisted Review
Technology Assisted Review significantly reduces review volume and costs, while greatly increasing efficiency and accuracy in the review process.
As technology improves and data sizes grow, machine learning technology is essential keep your reviews organized, focused, and efficient. But because legal technology is not standalone, our TAR experts are essential to the process of enhancing your review workflows and reducing your document volume.
The TLS e-discovery team of subject matter experts in analytics, AI, data privacy, and project management deploy pre-review and advanced analytics techniques to interrogate your data. We find patterns and trends, increase richness, and decrease the size of your data set, as well as classify information in regard to priority, privilege, and responsiveness.
By using TAR innovations, like predictive coding and continuous active learning to further inform and guide your review, our technologists, technology, and workflows produce effective results every time.
TAR Case Study
Use of Data Analytics and TAR for a Second Request
The Client
An Am Law 100 firm representing a global entertainment company that received a second request from the US Department of Justice (DOJ) in regard to an acquisition valued at $60 billion.
The Challenges
- Over 30 TBs of data collected in response to the second request
- 60 days to complete collection, processing, review, and production
- Unusually high volume of duplicative data due to uncommonly frequent backups by the client's cloud-based backup system
The TLS Solution
Faced with these difficult circumstances, TLS, outside counsel, and the corporate client rapidly deployed a highly customized workflow consisting of three major elements:
- Forensic de-duplication prior to ingestion
- Application of Pre-Review Analytics®
- Negotiation and implementation of TAR protocols
TLS's forensics consultants applied filters and de-duplication, reducing the data volume to just under 650 GBs for ingestion. Our project managers and discovery consultants actively engaged with outside counsel to gain DOJ approval on the application of Pre-Review Analytics®, TLS’s proprietary filtering that uses data analytics and artificial intelligence functions built into Digital Reef. This process further reduced the volume of data to around 410 GBs.
TLS and outside counsel engaged with the DOJ antitrust group to determine the parameters and protocols for the use of TAR, as well as production specifications. Utilizing a Brainspace logistic regression-based TAR workflow, a subject matter expert reviewed 5,040 "control" documents and an additional 1,750 "training" documents, after which the stipulated recall and precision rates were achieved—and 85% of the documents were coded.
After reviewing a statistically valid random sample of the non-responsive documents, the DOJ agreed that their demands had been met. Just under 222,000 documents were identified for production, and the client was able to meet their 60-day deadline without incurring additional costs.
TAR 1.0
Predictive Coding
Predictive coding technology can rapidly and accurately locate documents during the review process, saving you review time and spend. Predictive coding during e-discovery allows us to establish TAR success metrics and use them against the data set to provide reviewers with a complete and accurate control set. This can be used to create reports and training sets. 
TAR 2.0
Continuous Active Learning
Continuous active learning (CAL) allows us to identify the most relevant documents and data before passing them on to reviewers. TAR 2.0 has been widely adopted as the preferred method for document review because it eliminates barriers to entry and has become more user friendly. Cases that utilize a TAR 2.0 workflow often see an average reduction of 40–60 percent in the amount of documents that need to be reviewed. With data volumes constantly growing, using TAR 2.0 workflows are important for keeping document review efficient and cost-effective.
