By allowing the use of software, rather than lawyers, to sift through legal documents in the AB InBev deal, the Justice Department is likely to spark interest in such programs

Updated May 5, 2013, 8:47 p.m. ET

Document-Review Software Gets Boost From AB InBev Deal With Grupo Modelo



In the legal arena’s contest of man versus machine, the U.S. Justice Department has given a big boost to the machines.

Department officials reviewing the proposed merger of Anheuser-Busch InBev NVBUD +1.00% and Mexico’s Grupo Modelo GMODELO.MX -0.64% SAB recently approved a request to use software—rather than a horde of lawyers—to determine which documents needed to be turned over to the government.

Cases involving large companies often require legal counsel to sift through millions of electronic documents. In the past decade, that task has typically fallen on armies of contract, or temporary, lawyers who earn $25 to $40 an hour. Industry experts peg the cost for clients at more than $1 per document.A Catalyst


Only a handful of judges have approved the use of such data-review software in litigation, and law firms have been cautious about deploying the technology, which can be trained to hunt for concepts and unleashed across millions of documents at once.

But the Justice Department go-ahead is likely to spark more interest among companies looking to whittle down legal tabs.

In their review of the beer merger, Justice Department officials requested strategic plans, marketing and pricing information and other competitive data from spirits company Constellation Brands Inc., STZ +0.60% which the beer makers had lined up as a buyer for assets that would be sold in the deal, and Crown Imports LLC, a joint venture between Modelo and Constellation.

Lawyers for the companies identified a universe of more than a million documents that they would need to pick through in order to satisfy the government’s request.

With the blessing of the Justice Department’s antitrust division, the lawyers loaded the documents into a program and manually reviewed a batch to train the software to recognize relevant documents. The manual review was repeated until the Justice Department and Constellation were satisfied that the program could accurately predict relevance in the rest of the documents. Lawyers for Constellation and Crown Imports used software developed by kCura Corp., which lists the Justice Department as a client.

In the end, Constellation and Crown Imports turned over hundreds of thousands of documents to antitrust investigators.

The companies spent 50% less than they would have using more traditional methods, said Warren Rosborough, a partner at McDermott Will & Emery LLP who represented Constellation and Crown Imports. “Something that would easily cost three, four, five million dollars, you can do in the range of one to two,” Mr. Rosborough said.

Grupo Modelo and AB InBev agreed to sell Grupo’s entire U.S. business to Constellation. In return, the Justice Department dropped its challenge to the merger, clearing the way for AB InBev to acquire the 50% of Grupo Modelo it didn’t already own.

Grupo Modelo deferred to AB InBev, which declined to comment for this article.

Treading Carefully

A Justice Department spokeswoman declined to comment on the case but said the antitrust division “has worked with parties who choose to use this new technology in complying with the division’s civil investigative requests.” The division has also used such technology, commonly called predictive coding, for reviewing investigative documents internally, she said in an email.

Other government agencies, such as the Securities and Exchange Commission and the Federal Trade Commission, were more guarded about the technology, which is evolving. The SEC has no policy against use of predictive coding in enforcement matters, but a spokesman declined to say whether it had been used. The FTC has allowed the use of predictive coding on a case-by-case basis, a spokesman said, declining to give further details.

While predictive coding isn’t widespread, its popularity is growing, spurred by court rulings last year that blessed the use of the technology in civil cases, said Carla Walworth, a partner at Paul Hastings LLP.

Her firm is conducting a side-by-side comparison of human review and predictive coding, using client documents. Even if the software outperforms the humans, Ms. Walworth said, there are other considerations.

“More often than not, you’re trying to learn your case through the documents, and how will we substitute that function of learning from the documents when you’re using predictive coding?” she said.

Ms. Walworth said she is skeptical that the current technology is sophisticated enough to pick up all the nuances of language that could point to the building blocks of a case. “But who wants to pay to address all the nuances of language?”

About bambooinnovator
Kee Koon Boon (“KB”) is the co-founder and director of HERO Investment Management which provides specialized fund management and investment advisory services to the ARCHEA Asia HERO Innovators Fund (, the only Asian SMID-cap tech-focused fund in the industry. KB is an internationally featured investor rooted in the principles of value investing for over a decade as a fund manager and analyst in the Asian capital markets who started his career at a boutique hedge fund in Singapore where he was with the firm since 2002 and was also part of the core investment committee in significantly outperforming the index in the 10-year-plus-old flagship Asian fund. He was also the portfolio manager for Asia-Pacific equities at Korea’s largest mutual fund company. Prior to setting up the H.E.R.O. Innovators Fund, KB was the Chief Investment Officer & CEO of a Singapore Registered Fund Management Company (RFMC) where he is responsible for listed Asian equity investments. KB had taught accounting at the Singapore Management University (SMU) as a faculty member and also pioneered the 15-week course on Accounting Fraud in Asia as an official module at SMU. KB remains grateful and honored to be invited by Singapore’s financial regulator Monetary Authority of Singapore (MAS) to present to their top management team about implementing a world’s first fact-based forward-looking fraud detection framework to bring about benefits for the capital markets in Singapore and for the public and investment community. KB also served the community in sharing his insights in writing articles about value investing and corporate governance in the media that include Business Times, Straits Times, Jakarta Post, Manual of Ideas, Investopedia, TedXWallStreet. He had also presented in top investment, banking and finance conferences in America, Italy, Sydney, Cape Town, HK, China. He has trained CEOs, entrepreneurs, CFOs, management executives in business strategy & business model innovation in Singapore, HK and China.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: