What we’re thinking about

Insights, news, and tips from our top tech and business innovators.

Boosting eDiscovery with data analytics and artificial intelligence

afbleeding-avatar
Jeffrey Wolff |July 11, 2017|Read time: 1 min

Machine learning, technology-assisted review, text mining, predictive coding, and data analytics are all examples of techniques from the field of Artificial Intelligence (AI). These techniques have made eDiscovery smarter, faster and easier, as well as drastically reducing review costs.

In the eDiscovery process, techniques from AI are visible in three main areas:

  • Teaching computers human-like communication skills such as reading (Optical Character Recognition), dealing with speech (Audio Search) and with other languages (Machine Translation).
  • Advanced analytics and visualizations for Early Case Assessment (ECA).
  • Review accelerators such as Technology-Assisted Review (TAR) or auto-redaction and auto- pseudonymization.

Using computers for ECA and TAR has huge benefits: computers are faster, more accurate and consistently outperform human reviewers. By combining information extraction, and clustering machine learning and data visualizations, these tools can provide insight into correlations, patterns, trends and other important information. The same techniques are also used for auto-redaction and auto- pseudonymization.

TAR is based on machine learning and the semantic representation of text. eDiscovery solutions like ZyLAB ONE eDiscovery, use these techniques for automatic text and document classification to accelerate the review process by reducing the number of documents that need to be reviewed manually.

Lawyers regard the use of AI and data science techniques with caution. For technology and software companies like ZyLAB, supporting defensibility, and closely monitoring and measuring the process quality, is therefore equally as important as developing and applying these new techniques.

Out of the Black Box

Advances in education, the development of standards and best practices in the use of TAR and data analytics have resulted in greater clarity and acceptance of both processes. Driven by the ever-increasing need to filter massive data sets for efficiency, it probably will not be long before TAR and data analytics go mainstream.

0055 - old versus new airplanes - General Use

It is still not easy to grasp the full spectrum of methods varying from straightforward search-based, regular expressions and gazetteers (dictionaries), to advanced methods using natural language processing (NLP) and machine learning. In the technical guide on TAR we explain the different data analytic and machine learning techniques that you can use to boost performance in an eDiscovery process. More reading on how to use AI and data science techniques defensibly, you can find in our Trust Center.

Jeffrey Wolff
Jeffrey Wolff is a Certified E-Discovery Specialist who joined ZyLAB in May 2015 and serves as Director of E-Discovery Solutions. He brought with him over 20 years of experience in Information Systems and enterprise software. He has been involved in solution architecture, design, and implementation for major projects within the Department of Defense and Fortune 1000 corporations.

Share this blog post:

Get the latest ZyLAB updates