I am proud to announce the publication of a scholarly article I wrote this summer on my two favorite subjects, the proportionality doctrine and predictive coding. This was a real labor of love, although, truth be told, it was hell to write a law review article. After enduring the rigors of law student cite testing and editing, the article ended up seventy pages in length, with two-hundred and twenty-seven (227) footnotes! The students did a great job with academic and blue-book polish. The law journal will be released soon, ahead of schedule, but my readers can download a digital copy now. Predictive Coding and the Proportionality Doctrine: a Marriage Made in Big Data, 26 Regent U. Law Review 1 (2013-2014).
The intent here was to write an authoritative paper on proportionality and predictive coding, and, at the same time explain how these new developments support each other, and serve as the basis for my Bottom Line Driven approach to document review. It has been checked by a team a top-notch law review students and is suitable for court citation on a number of topics.
Predictive Coding and the Proportionality Doctrine: a Marriage Made in Big Data is the lead article in an issue focused on what the Journal calls a survey of emerging issues in electronic discovery. Two famed e-discovery judges made contributions to the Journal. The Forward for the Journal was written by Judge Andrew Jay Peck. Judge David J. Waxse wrote an article entitled Advancing the Goals of a “Just, Speedy, and Inexpensive” Determination of Every Action. Noted senior District Court Judge Henry Coke Morgan, Jr., of the District Court for the Eastern District of Virginia also contributed an article, Predictive Coding: a Trial Judge’s Perspective. Finally, attorney Monica McCarroll wrote an article for the Journal, Discovery and the Duty of Competence.
This new Regent Journal Volume 26 is not yet online, but I offer you this concluding paragraph from Judge Peck’s excellent Forward:
Almost seven years after the December 2006 Rule Amendments, the biggest problem remains the unfortunate fact that only a minority of counsel is e-discovery competent, while the majority still struggle. The principles and information contained in the articles in this issue – which include discussions of competency, cooperation, transparency, and proportionality, and advocate for the use of predictive coding – will bring more lawyers in the “Sedona Bubble” of e-discovery competence.
Judge Henry Morgan, Jr’s article, Predictive Coding: a Trial Judge’s Perspective, begins by stating if the parties are unable to reach an agreement on the production of ESI, or if their agreement “fails to produce results,” then courts should order the use of predictive coding. That is because predictive coding “appears to be the preferred path to promoting the objectives of Federal Rule of Civil Procedure One (“Rule One”).” Judge Morgan then summarizes his article as follows:
This Article suggests that trial courts should adopt predictive coding as it appears to be an improvement upon simple keyword or manual-search systems. As the cost of civil litigation continues to escalate, primarily driven by ever increasing discovery and pre-trial motion practice, immediate solutions should be sought, or the civil jury trial will face obsolescence as a method of resolving civil disputes over money damages and property rights. Minimizing the costs of handling ESI is only one of the many facets of controlling the costs of civil litigation, but it is an increasingly important facet, and controlling litigation costs has important long-term consequences for both the bench and bar. This Article, therefore, addresses the question of whether predictive coding promotes the underlying principles of Rule One. Given the threefold nature of these principles, the analysis proceeds in three parts to reach the conclusion that predictive coding represents a positive step toward achieving just, speedy and inexpensive trials.
Well said Judge Morgan. This helps put our work in perspective. I suggest everyone read this article, indeed, read all of the articles in this Journal and cite to them in future legal memorandums.
The full title of Judge Waxse’s article is Advancing the Goals of a “Just, Speedy, and Inexpensive” Determination of Every Action: The Recent Changes to the District of Kansas Guidelines for Cases involving Electronically Stored Information. Judge Waxse explains the new guidelines of his court and how they are designed to address two out of the three primary causes of e-discovery waste and expense: lawyers’ lack of technical competence and lack of cooperation. The third cause is the ever increasing volume of ESI maintained by litigants. Of course, court guidelines cannot stem the exploding clouds of information, nothing can (although information governance can help), but guidelines can help lawyers with competence and cooperation.
Monica McCarroll’s article, Discovery and the Duty of Competence, elaborates on the core problem of lawyer incompetence. Monica states that the goal of her article is to outline the knowledge, skill, thoroughness and preparation a litigator should possess to competently represent a client engaged in civil discovery in federal court today. Her article sets forth the key cases and e-discovery knowledge that every competent lawyer should know. This is a good 30-page collection of case law and commentary supported by 118 footnotes.
The two paragraph introduction to my article, Predictive Coding and the Proportionality Doctrine: a Marriage Made in Big Data, summarizes it contents:
The search of electronic data to try to find evidence for use at trial has always been difficult and expensive. Over the past few years, the advent of Big Data, where both individuals and organizations retain vast amounts of complex electronic information, has significantly compounded these problems. The legal doctrine of proportionality responds to these problems by attempting to constrain the costs and burdens of discovery to what are reasonable. A balance is sought between the projected burdens and likely benefits of proposed discovery, considering the issues and value of the case. Several software programs on the market today have responded to the challenges of Big Data by implementing a form of artificial intelligence (“AI”) known as active machine learning to help lawyers review electronic documents. This Article discusses these issues and shows that AI-enhanced document review directly supports the doctrine of proportionality. When used together, proportionality and predictive coding provide a viable, longterm solution to the problems and opportunities of the legal search of Big Data.
To demonstrate the combined effectiveness of proportionality and predictive coding, this Article is organized into four parts. Part I discusses how the rapid growth of electronic information drives the rising costs of civil litigation as discovery becomes increasingly expensive. This section also introduces proportionality and predictive coding as means of combating rising costs. Next, Part II explains how AI can be harnessed in document review, noting applicable case law and providing a detailed description of the predictive coding process. Then, Part III proceeds to consider the legal doctrine of proportionality—in other words, balancing the burden of e-discovery with its benefits—and considers relevant case law. Finally, Part IV concludes by demonstrating the close relationship between predictive coding and proportionality, observing that predictive coding allows one to fine-tune discovery in any case to the anticipated value of the suit against the projected costs of document review.
For more detail on what my article covers, take a look at the Table of Contents (which, by the way, is an example of metadata):
TABLE OF CONTENTS
I. THE HIGH COSTS OF LITIGATION ARISE PRIMARILY FROM EXPLODING VOLUMES OF DIGITAL INFORMATION
A. Paradigm Shift
B. Lawyers Overwhelmed by Rapid Advances in Technology
C. Failure of Our Law Schools and Law Firm Training
D. Processes and Methods Designed for Search and Review of Paper Documents Do Not Work When Applied to High Volumes of ESI
E. Cheap Lawyers Are Not the Answer
F. The Answer Lies in Predictive Coding and Proportionality
G. RAND Report on Litigation Expenses
H. Two-Fold Solution
II. THE USE OF ARTIFICIAL INTELLIGENCE IN DOCUMENT REVIEW
A. Active Machine Learning Explained
B. Predictive Coding Case Law
C. Six-Step and Eight-Step Predictive Coding Work Flows
A. Origins of the Proportionality Doctrine
B. Flexible Application of Cost-Burden Analysis
C. Importance of Early Assertion of Proportionality
1. Very Late Assertion
2. Late Assertion
3. Timely Assertion
D. Proportionality Requires Justice, as Well as Speed and Efficiency: Criticisms of DCG Systems and the Patent Bar Model Order
E. The Growing Influence of the Proportionality Doctrine
IV. HOW PREDICTIVE CODING SUPPORTS PROPORTIONALITY
A. Two Stages of Document Review Using Predictive Coding
B. Bottom-Line-Driven Proportional Review and Production
1. Setting a Budget Proportional to the Case
2. Small Case Example
3. Estimate of Projected Costs
4. A Big Data Example
5. All Review Projects Are Different
C. The More-Bang-for-the-Buck-Bottom-Line-Ranked Approach Is Good for Both the Requesting Party and the Producing Party
Readers of this blog will find the material in my law review article to be very familiar. It does not plough new ground, but presents the information in a formal style with full citations. Please consider reading this over the holiday season. Even if you only have time for a quick skim, be a saint and include a citation in your future legal memorandums. Predictive Coding and the Proportionality Doctrine: a Marriage Made in Big Data, 26 Regent U. Law Review 1 (2013-2014). Please do the same for the other contributors, Judges Waxse, Morgan and Peck, and attorney, Monica McCarroll.
To all judges reading this blog, I hope you will consider including a citation of these articles in your future opinions. That is about the only reward we practicing attorneys and judges get for writing such articles. Unless, of course, there really is an after-life, in which case, I will probably receive quite a few pokes with a pitch fork for frittering away my time with such earthly vanities. Hopefully my fellow contributors will not suffer a similar fate.
[…] e-Discovery Team: Predictive Coding and Proportionality: A Marriage Made In Heaven […]