Using eDiscovery analytics is a win-win scenario: higher-quality review at lower cost. Part one of this article described how analytics can be used strategically to improve review efficiency by grouping related documents and cut costs by leveraging technology to cull non-responsive documents. In part two, I give two more strategic reasons to use analytics.
Reason #3: Prioritize and assign documents for review
The third reason to use eDiscovery analytics is to make the most efficient staffing assignments. Reviewers aren’t interchangeable. Variables include document review experience, subject matter knowledge, availability, billable rate and more.
It only makes sense to “match” reviewers and document batches. For example, complex technical or financial documents should be assigned to subject matter experts for review. On the other hand, routine correspondence can be assigned based on reviewer availability or billable rate.
Analytics makes it possible to prioritize review based on issues or relevance. For example, concept analysis can be used to prioritize review of the most relevant documents based on issues.
Predictive coding is an excellent tool for combining the goals of prioritizing review and making overall staffing decisions based on relevance. Predictive coding is a type of technology assisted review (TAR). It uses a computer algorithm to analyze each document in the dataset and predict how likely it is to be responsive. The algorithm assigns a percentage likelihood of responsiveness to each document (e.g., 84% likely to be responsive, 27% likely to be responsive).
The predictive coding workflow includes quality control measures to ensure that the result meets the pre-determined accuracy target. The accuracy target is typically decided by the case team in consultation with their eDiscovery service provider. It may also be negotiated with opposing counsel.
Predictive coding is widely used to allocate less relevant documents to lower cost reviewers. For instance, documents below a certain threshold – say 65% likelihood of relevance – could be outsourced to lower-cost contract reviewers. Documents above the threshold could be kept in-house for review by the firm’s lawyers and paralegals assigned to the case.
Cost isn’t the only consideration. It’s important to find and review the most relevant documents as quickly as possible. With predictive coding, the top tier of documents most likely to be relevant can be set aside for review by a lawyer with deep subject matter knowledge.
Although the most common context for predictive coding is responsiveness review, it can also be used to facilitate early settlement. Most cases ultimately come down to a few hundred critical documents. Before investing in full-scale review, you can use predictive coding to identify the small universe of documents that are most likely to decide the case. Prioritizing review of these key documents supports informed decision-making about settlement.
Reason #4: Better issue spotting
The fourth reason to use eDiscovery analytics is issue spotting. Analytics improves substantive review for issues in connection with deposition preparation and motions. This is equally true for review of the client’s documents and review of opposing or third-party productions.
Analytics can be used to issue spot in two main ways. First, to identify new issues. Second, to find additional documents related to known issues. Concept analysis tools such as clustering are particularly helpful in issue spotting.
Two other pertinent examples of concept analysis tools from Relativity are keyword expansion and find similar documents. In keyword expansion, you enter a search term into the tool and it returns other keywords in your data that conceptually match your search term. For instance, you could input a product name. Keyword expansion can identify the internal code names used for the product when it was still in development.
To use find similar documents, you first tag a document that’s relevant to an issue in your case. The tool will retrieve documents that are conceptually similar to the exemplar you identified. This can be especially helpful in assessing the opposing party’s production. Tag a document in your client’s files that exemplifies a key issue in order to prioritize review of relevant documents in the opposing production. Conversely, if the analytics tool doesn’t find any relevant documents, that may indicate the production is deficient.
Relativity’s concept analysis tools use the database index that was built during processing. Unlike a thesaurus, concept analysis is based on the actual documents in the review database. Ask your eDiscovery service provider for more information on concept analysis tools, as details vary across eDiscovery platforms.
The analytics strategy for your case should be crafted to achieve your review goals. Review goals are case-specific. They take into account the litigation plan, data volume and types, substantive issues and practical considerations of staffing, budget and deadlines.
When used strategically, analytics are an invaluable resource in meeting your review goals. Consult with your eDiscovery service provider to identify the analytics tools that are right for your case.
Helen Geib is General Counsel and Practice Support Consultant for QDiscovery. Prior to joining QDiscovery, Helen practiced law in the intellectual property litigation department of Barnes and Thornburg’s Indianapolis office where her responsibilities included managing large scale discovery and motion practice. She brings that experience and perspective to her work as an eDiscovery consultant. She also provides trial consulting services in civil and criminal cases. Helen has published articles on topics in eDiscovery and trial technology. She is a member of the bar of the State of Indiana and the US District Court for the Southern District of Indiana and a registered patent attorney.
This post is for general informational and educational purposes only. It is not intended as legal advice or to substitute for legal counsel, and does not create an attorney-client privilege.