Washington D.C. office of counsel Jason R. Baron is lead co-editor of Perspectives on Predictive Coding and Other Advanced Search Methods for the Legal Practitioner, a 600-plus page book recently published by the American Bar Association. The book discusses the current state of search methodology and examines the future of e-discovery in investigations, information governance and other legal contexts. It includes chapters Jason co-authored with Drinker Biddle lawyers Tracy Drynan, senior attorney, and Bennett Borden, chief data scientist and partner.
In this Q&A, Jason discusses predictive coding, the book’s intended audience and the ties between e-discovery search techniques and analytics used in information governance practice.
Q: What were you trying to accomplish with this book?
JRB: This book attempts to educate lawyers about the latest techniques used in searching electronically stored information for litigation and other purposes. In 2012, Judge Andrew Peck’s opinion in the Da Silva Moore case gave a judicial blessing to the use of predictive coding in e-discovery. However, to most lawyers, predictive coding still remains somewhat mysterious, and there is a reluctance on the part of some to embrace a “brave new world” of algorithms and analytics in assisting in civil discovery and related contexts. Given this state of affairs, Michael Berman approached me a few years back with the idea that a book on advanced search techniques would be of value to the legal profession. I, in turn asked Ralph Losey, one of the leading evangelists in the legal community on the subject of search, to join in our efforts.
Q: Please define what predictive coding is.
JRB: Predictive coding, as it is primarily used in e-discovery, is a method for distinguishing between relevant and non-relevant documents, based on coding decisions made by subject matter experts to “train” an algorithm to quickly sort and classify large quantities of documents. The same types of algorithms are being increasingly used for classifying documents in other ways as well, across a spectrum of related types of investigations and in furtherance of information governance policies.
Q: How did you go about picking chapter authors and subjects?
JRB: As I said in the Introduction to the book, I have been fortunate to encounter a number of brilliant lawyers and scholars at the cutting edge of e-discovery and information science during the past decade and a half, through my past participation in editing commentaries for The Sedona Conference, in my co-founding of the TREC Legal Track, and in my role in creating what we call the “DESI” (Discovery of ESI) series of international workshops for academics and lawyers. The book contains a wide cross-section of perspectives from judges, lawyers, PhDs in computer and information science, as well as other leading figures at law firms and industry solution providers.
Q: Is the book only for advanced e-discovery geeks and techies . . . or is it for a wider legal audience?
JRB: The book is meant to appeal both to practitioners who are seeking knowledge of what predictive coding and other advanced search methods are all about, as well as to those members of the legal community who are “inside the bubble” of e-discovery already and wish to be exposed to the latest, cutting-edge techniques. I would also hope that the book would be valuable to lawyers who do not consider themselves litigators or e-discovery practitioners, but who wish to apply a knowledge of smart analytics in a variety of other legal contexts.
Q: I see you cover information governance in a separate section. What's the tie-in here to e-discovery?
JRB: Information governance (IG) recently has emerged as a discipline aimed at providing a coherent approach to issues surrounding the ever-increasing accumulation of data in private and public institutions. There are any number of facets of IG that benefit from using advanced analytical techniques, including involving the classification and remediation of electronically stored information. At almost every e-discovery conference one attends, there is an emphatic plea that corporations and institutions of all types get their “data house in order,” as a way of reducing the burdens imposed by litigation. Knowledge of advanced search techniques can be of enormous benefit to the practitioner interested in reducing corporate risk as part of an IG program.
Q: Is the book in danger of being rendered obsolete in a few years by the rapid pace of technology?
JRB: The short answer is: yes, of course. As I said in my Introduction, the editors are attempting here to catch “lightning in a bottle” -- namely, we have sought to provide a set of perspectives on predictive coding and other advanced search techniques as they are used today. I went onto say that we are “painfully aware that the shelf-life of publications such as the present work is not long.” However, the good news (at least for the ABA as a publisher), is that the ideas set out in the book related to using advanced search techniques have yet to substantially percolate through the legal profession. I would estimate that many legal practitioners have not had much exposure to these state of the art techniques, and can learn a lot. And for my fellow e-discovery and IG aficionados, I am sure you can find something in the volume which will either validate your expertise or provoke you into challenging prevailing wisdom through your own future written contributions!
Q: Anything else you would like to say?
JRB: I am enormously grateful to Judge Peck for contributing a Foreword and to all the chapter authors who contributed substantial time over the last couple of years in making this pro bono project for the ABA a success. Finally, I would like to reiterate what I said in my Introduction: for some, the prospect of needing to be technically competent in advanced search techniques may lead to considerations of early retirement. For others, the idea that lawyers may benefit from embracing predictive coding and other advanced technologies to lower the costs and burdens of litigation is exhilarating. I am hopeful (as I am sure that the ABA is as well) that there are more readers in the latter category!
An event to celebrate the publication of this book will take place on January 30th at the New York City offices of Drinker Biddle from 6-8 PM. Please contact Iwona.stepniak dbr.com for more details and to register.