Technology

DISCO Announces New Artificial Intelligence Platform For eDiscovery

Boasting the latest in machine learning capabilities, DISCO has big plans for changing eDiscovery.

By  
on

globe globalization world tech technologyAt its latest glitzy product unveiling, Apple introduced the world to the HomePod, a Siri-enabled speaker/home assistant to compete with the Amazon Echo and Google Home. Unfortunately, they turned Siri into an ominous reflection of the most famously deadly housekeeping artificial intelligence of all time. Nothing salves those technophobic fears like knowing your Apple is going to lock you out of the house someday.

Meanwhile, the legal industry saw a different artificial intelligence unveiling from CS DISCO, opening up its DISCO AI platform for the general use of all DISCO customers. It’s an AI product launch with a mercifully less murderous overtone than Apple’s. On the other hand, listen to the Bee Gees for about five minutes, and perhaps the name DISCO will evoke just as much bloodlust.

DISCO’s new AI platform harnesses “the latest advancements in both machine learning and cloud computing” to streamline the eDiscovery process. That’s a fancy way of saying that DISCO has a tool that’s going to start learning alongside the reviewers, taking the human input and integrating it into its own read of the documents, opening up new efficiencies.

Working in the background during the normal course of a review, DISCO AI displays Tag Predictions — a suggested tag with a score from -100 to +100, indicating the likelihood that the tag should be applied to the document by a human — in real-time.

The results seen during the limited availability phase of DISCO AI are impressive. The platform’s ability to correctly predict the likelihood that a tag should or should not be applied to a document is consistently in the 85% to 95% range, even with as few as 50 examples and data sets as small as 2,000 documents.

That’s a tremendous tool for document reviews and a marked improvement over many of the technology-assisted-review systems of yesteryear. Assuming the long-term goal of a platform like this is to learn enough through a sample set that lawyers are confident allowing the AI to perform a first pass of large amounts of data, the capacity to actually learn from reviewers in context rather than take a clunky set of instructions is invaluable. Lawyers aren’t programmers, after all, and those attorney-generated lists of relevant terms deliberately fed into programs always left something to be desired.

DISCO AI’s accuracy vis a vis human reviewers — upwards of 95 percent — is undeniably worth touting, but anyone who’s ever worked on a big review knows the other side of the coin is a far bigger danger. With the DISCO AI platform, quality control is able to say “here are documents that don’t have the X tag that AI expects should have that tag — is there something systematically wrong with one specific reviewer?” While that might not seem as sexy as some of the other applications of this system, it’s hard to undersell the practical importance of that service. Because, let’s face it, some lawyers are dumb.

While the opportunity to see tag predictions in real-time provides a useful “driver assist” to a reviewer, helping them accurately tag documents by flagging key issues, this function can also be shut off to prevent reviewers from relying too heavily on the system’s predictions (or lack thereof). It’s all adaptable to the type of review required.

Sponsored

“I am excited DISCO AI is bringing deep learning to ediscovery, which I anticipate will dramatically improve the speed and accuracy of document analysis and minimize traditional review,” stated Gordon Calhoun, Partner and Chair of the Electronic Discovery, Information Management & Compliance Practice at Lewis, Brisbois, Bisgaard & Smith LLP. “Deep learning neural nets have the potential to take us beyond text data, allow us to better understand the evidentiary value of the cocoon of data that surrounds us and use the IoT as a virtual witness in the courtroom. I expect these advances will transform many other areas of the practice of law, as well.”

I guess when I said earlier that DISCO AI aims to streamline the eDiscovery process, I should have said that DISCO AI aims to streamline the eDiscovery process… for now. Because as Calhoun points out, there’s nothing stopping DISCO from applying this technology to any number of legal processes — on either the litigation or transactional side.

HeadshotJoe Patrice is an editor at Above the Law and co-host of Thinking Like A Lawyer. Feel free to email any tips, questions, or comments. Follow him on Twitter if you’re interested in law, politics, and a healthy dose of college sports news.

Sponsored

CRM Banner

Topics

, , , , ,