At the Federation of Defense and Corporate Counsel (FDCC) annual meeting, I recently attended an excellent program on predictive coding presented by Howard Merten of Partridge, Snow & Hahn in Providence, RI, Matt Nelson of Symantec, and Magistrate Judge Andrew Peck of the Southern District of New York (who has written a leading article and one of the leading court decisions on this issue, see my March 9, 2012 post for more).  For those who are not familiar with it, predictive coding is a relatively new software-based document review platform that uses computer algorithms to identify relevant/responsive documents.  First, a review set of potentially-relevant documents is gathered by the producing party and loaded into the system.  Second, a set of more senior-level attorneys (not junior associates or contract lawyers) reviews a sample set of documents for relevance, coding them for their degree of relevance.  Then the software itself identifies relevant documents in the remainder of the review set.  The human reviewers then review again to help the computer refine its analysis, through an iterative process.

Here are some key points I gleaned from the presentation: 

  • Predictive coding is clearly cheaper than traditional review.  A case study cited by the presenters suggested that with 100,000 documents, traditional manual review might cost approximately $140,000, whereas with predictive coding the attorneys’ fees might be as low as $9,600, plus the electronic discovery vendor fees, and the cost of reviewing the documents identified by the computer as relevant to confirm relevance and that they are not privileged.  Predictive coding has also been shown to be more accurate because the computer doesn’t get tired unlike young lawyers who are spending countless hours in front of a screen. 
  • The system will rank documents by degree of responsiveness, which is a key time-saver, helping the litigation team get to the most relevant documents faster.  The secondary review process for a large production can be segmented so that the senior lawyers review the documents that the computer identifies as most relevant and junior lawyers or contract attorneys review the documents the computer identifies as least relevant. 
  • In the limited court decisions on this, where the producing party has asked the court for approval, courts have uniformly approved the use of predictive coding.  Where the requesting party asks the court to force the producing party to use predictive coding there has been some resistance, but this still might be possible if you ask early, before the other side spends a bunch of money on manual review.  (In class actions that is essentially irrelevant because it would be the very rare case where the plaintiffs would have a large number of documents anyway.) 
  • The key sticking point can be if the opposing party expresses a concern that the producing party will “game the system” by marking “hot” documents as non-responsive.  There are various approaches to deal with this involving quality control checks and some transparency. 
  • Because predictive coding is word-based, it will not work for photographs, drawings, spreadsheets and the like, which need to be dealt with separately. 
  • Judge Peck reminded everyone about taking advantage of Fed. R. Evid. 502(d), which allows a court to issue an order regarding non-waiver of privilege for privileged documents that slip through the review process.  He suggested asking for a Rule 502(d) order in cases involving large productions.  In my experience, this is often also built into a confidentiality/protective order.
Email this postTweet this postLike this postShare this post on LinkedIn
Photo of Wystan Ackerman Wystan Ackerman

I am a partner at the law firm of Robinson+Cole in Hartford, Connecticut, USA.  My contact information is on the contact page of my blog.  I really enjoy receiving questions, comments, suggestions and even criticism from readers.  So please e-mail me if you…

I am a partner at the law firm of Robinson+Cole in Hartford, Connecticut, USA.  My contact information is on the contact page of my blog.  I really enjoy receiving questions, comments, suggestions and even criticism from readers.  So please e-mail me if you have something to say.  For those looking for my detailed law firm bio, click here.  If you want a more light-hearted and hopefully more interesting summary, read on:

People often ask about my unusual first name, Wystan.  It’s pronounced WISS-ten.  It’s not Winston.  There is no “n” in the middle.  It comes from my father’s favorite poet, W.H. (Wystan Hugh) Auden.  I’ve grown to like the fact that because my name is unusual people tend to remember it better, even if they don’t pronounce it right (and there is no need for anyone to use my last name because I’m always the only Wystan).

I grew up in Deep River, Connecticut, a small town on the west side of the Connecticut River in the south central part of the state.  I’ve always had strong interests in history, politics and baseball.  My heroes growing up were Abraham Lincoln and Wade Boggs (at that time the third baseman for the Boston Red Sox).  I think it was my early fascination with Lincoln that drove me to practice law.  I went to high school at The Williams School in New London, Connecticut, where I edited the school newspaper, played baseball, and was primarily responsible for the installation of a flag pole near the school entrance (it seemed like every other school had one but until my class raised the money and bought one at my urging, Williams had no flag pole).  As a high school senior, my interest in history and politics led me to score high enough on a test of those subjects to be chosen as one of Connecticut’s two delegates to the U.S. Senate Youth Program, which further solidified my interest in law and government.  One of my mentors at Williams was of the view that there were far too many lawyers and I should find something more useful to do, but if I really had to be a lawyer there was always room for one more.  I eventually decided to be that “one more.”  I went on to Bowdoin College, where I wrote for the Bowdoin Orient and majored in government, but took a lot of math classes because I found college math interesting and challenging.  I then went to Columbia Law School, where I was lucky enough to be selected as one of the minions who spent their time fastidiously cite-checking and Blue booking hundred-plus-page articles in the Columbia Law Review.  I also interned in the chambers of then-Judge Sonia Sotomayor when she was a relatively new judge on the Second Circuit, my only connection to someone who now has one-ninth of the last word on what constitutes the law of our land.  I graduated from Columbia in 2001, then worked at Skadden Arps in Boston before returning to Connecticut and joining Robinson+Cole, one of the largest Connecticut-based law firms.  At the end of 2008, I was elected a partner at Robinson+Cole.

I’ve worked on class actions since the start of my career at Skadden.  Being in the insurance capital of Hartford, we have a national insurance litigation practice and I was fortunate to have the opportunity to work on some prominent class actions arising from the 2004 hurricanes in Florida and later Hurricane Katrina, including cases involving the applicability of the flood exclusion, statutes known as valued policy laws, and various other issues.  My interest and experience in class actions gradually led me to focus on that area.

In Connecticut courts I’ve defended various kinds of class actions that go beyond insurance, including cases involving products liability, securities, financial services and consumer contracts.

My insurance class action practice usually takes me outside of Connecticut.  I’ve had the pleasure of working on cases in various federal and state courts and collaborating with great lawyers across the country.  While class actions are an increasingly large part of my practice, I don’t do exclusively class action work.  The rest of my practice involves litigating insurance coverage cases, often at the appellate level.  That also frequently takes me outside of Connecticut.  A highlight of my career thus far was working on Standard Fire Ins. Co. v. Knowles, the U.S. Supreme Court’s first Class Action Fairness Act case.  I was Counsel of Record for Standard Fire on the cert petition, and had the pleasure of working with Ted Boutrous on the merits briefing and oral argument.

I started this blog because writing is one of my favorite things to do and I enjoy following developments in class action law, writing about them and engaging in discussion with others who have an in interest in this area.  It’s a welcome break from day-to-day practice, keeps me current, broadens my network and results in some new business.

When I’m not at my desk or flying around the country trying to save insurance companies from the plaintiffs’ bar, or attending a conference on class actions or insurance litigation (for more on those, see the Seminars/Programs page of this blog), I often can be found playing or reading with my young daughter, helping my wife with her real estate and mortgage businesses, reading a book about history or politics, or watching the Boston Red Sox (I managed to find bleacher seats for Game 2 of the 2004 World Series when Curt Schilling pitched with the bloody sock).  When the weather is good I also love to take the ferry to Block Island, Rhode Island and ride a bike or walk the trails there. If you go, I highly recommend the Clay Head Trail.