eDiscovery: New Horizons for Corporate Legal Teams

Leverage machine learning via the cloud to improve eDiscovery efficiency and slash costs.

istock 155148711
iStock

The intersection of law and IT is a busy place. Litigation and investigations are surging, fueled by regulatory compliance mandates (including data privacy laws), even as sophisticated cyberattacks target that very information—resulting in more investigations and litigation. Legal departments and law firms are beset by tight budgets and constrained IT resources. The pandemic added further complications, forcing lawyers to work remotely, while spurring increased legal activity.

Caught in the middle is the vital task of electronic discovery, which is being stretched to the limit by unprecedented volumes of data. eDiscovery— the most expensive part of litigation—is the process of identifying, preserving, collecting, searching and reviewing documents to find the relevant information to the legal matter, and producing the relevant documents as needed.

In the face of these forces, what’s needed is a cloud-based platform that provides secure, seamless, and reliable access to data and the advanced tools for rapid decision-making and risk management, without requiring IT handholding.

Technology-assisted review reduces costs and improves efficiency amidst resource constraints

Because the law is a human endeavor, there is no substitute for human knowledge and judgment when it comes to the discovery process. However, the increase in litigation, investigations and regulatory compliance matters, multiplied by the sheer amount of data in all its forms—email, documents, spreadsheets, images, video, audio files, third-party apps, chat and other forms of ephemeral data—create far too much information for humans to review manually and meet demanding timelines. Help, in the form of machine learning (ML), is needed.  

Technology-assisted review (TAR), also knows as predictive coding or computer-assisted review, is a process whereby humans leverage technology to efficiently identify specific documents in a vast and disorganized corpus. Every TAR system encompasses human review for a portion of a document collection to train computers that, in turn, extrapolate those human judgments.

Newer forms of TAR are based on continuous machine or continuous active learning.  With TAR, legal teams can gain early and important insight to quickly understand and intelligently organize data, resulting in improved review efficiency and cost savings by minimizing the overall volume of documents warranting legal review.

eDiscovery technology such as OpenText™ Axcelerate™ and OpenText™ Insight uses TAR to rapidly sift through often massive volumes documents—sometimes in the millions for certain cases—to prioritize documents that are most likely relevant to the matter, surfacing first those most likely to relevant for human review. Document rankings are continuously updated to take advantage of additional judgments by reviewers in real-time. As training continues, the algorithm and document rankings continuously improve so the review team finds relevant documents faster.

When used correctly, TAR has the potential to offer tremendous savings, both in review time and cost, without sacrificing the quality of results. With TAR, review teams can work faster and process documents that are most likely to be relevant first. A relatively simple sampling process within TAR, showing the percentage of relevant documents found, can also give the review team a reasonable, defensible basis for concluding a review when the search objectives have been satisfied.

Bottom line: Corporate legal departments are under pressure like never before, from an increase in litigation and investigations as organizations strive to comply with new regulations, to stretched resources and tight budgets. Cloud-based eDiscovery from OpenText provides lawyers the secure, seamless, and reliable access to case data, along with full functionality including TAR, that they need for rapid decision-making and sound risk management.

For more information, visit: www.opentext.com/discovery

Related:

Copyright © 2021 IDG Communications, Inc.