Technology Assisted Review

Advanced Analytics

MCS is proud to be a Blue-level Relativity Best in Service partner. As a leading eDiscovery service provider, MCS has integrated the Relativity eDiscovery platform to deliver feature-rich capabilities for web-based document review and analysis.

Through a voluntary audit, MCS demonstrated expertise and experience with hosting projects in Relativity to earn Best in Service status. Relativity evaluates Best in Service partners’ individual data centers based on technical infrastructure, customer service and product knowledge. Additional criteria include duration as a hosting partner, size of Relativity installation and core Relativity certifications. By partnering with MCS, clients have access to Relativity in an environment that continuously exceeds system performance and service delivery standards. All projects are managed by Relativity-certified and industry-certified consultants with over 15 years of electronic discovery experience.

Relativity's structural analytics, conceptual analytics and assisted review play an important role in the development of MCS's intelligent review workflow. With the expertise of MCS's dedicated support team and Relativity's advanced technology, you will receive the best review workflow customization in the industry.

Relativity Structural Analytics

Relativity's Structural Analytics allows us to quickly assess and organize a large, unfamiliar set of documents. You can either batch out these groups of documents for review or use them to create new document sets for further analysis. We are able to use these groups to run structured data operations to shorten review time, improve coding consistency, optimize batch set creation and improve your analytics indexes. 

• Email threading makes reviewing a single conversation as simple as possible by identifying email relationships and any attachments included in the email chain, then extracting and normalizing metadata.
  
• Near-duplicate detection allows us to quickly locate and group together documents containing highly similar content.
  
• Language identification examines the extracted text of each document to group them by language.

Relativity Conceptual Analytics

Relativity conceptual analytics uses an index to identify similar ideas or concepts within a document set, making the process faster and more efficient than matching specific search terms as done by traditional search engines.

With this program, MCS is able to perform the following searching techniques:

• Conceptual Term Searching: Returns documents that contain concepts similar to your search terms or phrases.
  
• Keyword Expansion: Returns keywords that conceptually match your search term.
  
• Categorization: Uses a set of example documents as the basis for categorizing other conceptually similar documents.
  
• Clustering: Identifies and groups conceptually similar documents in a workspace using an existing Relativity Analytics index. It does not require a training or example set of documents.
  
• Find Similar Documents: Uses the document currently displayed in the viewer to identify other conceptually correlated documents.
  
• Similar Document Detection: Identifies groups of highly correlated documents and displays them as related items in Relativity.
  

Relativity Assisted Review

Relativity Assisted Review is a computer-assisted review workflow that combines process and technology to allow flexibility and document transparency. This statistical approach for auto-ranking responsiveness of documents is known as predictive coding.

Predictive Coding Workflow:

1. Review teams begin by coding a sample set of documents. By manually reviewing statistically relevant subsets of documents coded by the computer, you can ensure accuracy and validate your results.
2. Relativity then categorizes the rest of the documents in a case. Reviewers will either agree or disagree with how Relativity has categorized a document. This allows you to train the system, so Relativity will actually learn and make better decisions as your review team continues to code. 
3. You can validate Relativity’s decisions by manually reviewing statistically relevant subsets of documents to ensure coding accuracy. Once your team starts consistently agreeing with how Relativity is categorizing documents, you can move to the next phase of your project.

This program orders documents from the most responsive to the least responsive, and our team will analyze the percentage of responsive documents as well as the percentage of correctly coded documents to determine when the review is finished.

Active Learning

Active learning puts the most relevant documents in your reviewers’ hands—fast. It does this by continually learning, in real time, from your team’s coding decisions and using those decisions to deliver the documents that matter most.   

Relativity AL keeps tabs on coding decisions in real time to refine its understanding of what’s responsive. As your project progresses and reviewers code more documents, the engine gets smarter, analyzing the coding decisions and constantly refining its understanding of what’s most important to your matter—so you can get to the relevant information faster.  It can also be combined with other analytics tools to enhance the review.  For instance, running email threading to eliminate non-inclusive emails and duplicate spares, then running Active Learning on what's left.  

Read more about Active Learning and Artificial Intelligence in document review in our blog post here.