How to Get Smart About E-Discovery

catalystsecure.com

How to Get Smart About E-Discovery

Shawn Cheadle, J.D. Mark Noel, J.D.

Mark Noel

Presenters

Shawn Cheadle

Managing Director, Professional Services Catalyst Repository Systems [email protected]

General Counsel Military Space, Lockheed Martin Space Systems Co. [email protected]

Agenda

How big data is changing litigation

E-discovery 101 and its challenges

Court decisions that open the door to cost-saving technology

Lessons learned from larger corporations

What this means to business leaders

Q&A

Recent E-Discovery Sanctions

Rambus — $250 million (2013)

In re Pradaxa Products — $1 million (2013)

Victor Stanley v. Creative Pipe — $1.05 million (2011)

Soaring Costs and Greater Risk

E-discovery costs skyrocketing

Review costs skyrocketing

Data spread across multiple cases, firms, and vendors

Exploding content

The Problem:

1.8 Zettabytes a year Library of Congress: 30 Terabytes

60 Million Libraries a year...

... and growing

“The 1% Problem”

“The 1% Problem”

Facing the Corporate Challenges

Three Broad Categories:

Document Review Tasks

1. Classify

2. Protect

3. Discover

Recall

“How complete was my catch?”

Precision

“How pure was my catch?”

Which bucket does each document go into?

1. Classify

Recall? Reasonably high

Precision? Reasonably high

Think Sedona Conference and FRCP 1, 26

1. Classify

2. Protect

Recall? 100% – nothing escapes

Precision? Usually high, especially

if you have to log it all

Make sure no sensitive or privileged info gets out

2. Protect

3. Discover Recall? Don’t really care

Precision? Really good – don’t waste our time with junk.

Most -like.

What can we learn from the documents’ contents?

3. Discover

“It ain't what you don't know that gets you into trouble. It's what you know for sure that just ain't so.”

– Mark Twain

Research on Search Terms

20%

75% Attorneys worked with experienced paralegals to develop search terms. Upon finishing, they estimated that they had retrieved at least three quarters of all relevant documents.

What they actually retrieved:

Blair & Maron, An Evaluation of Retrieval Effectiveness for a Full-Text Document-Retrieval System (1985).

Research on Search Terms

Counsel and others need interactive access to the ESI population in order to achieve at least 50% retrieval of responsive ESI.

– Some Lessons Learned To Date from the TREC Legal Track

Employing different combinations of search technologies (and others) results in the retrieval of approximately 78% of the total number of relevant documents. In effect, using a variety of methods and tools will increase the search results substantially.

– In Search of the Perfect Search

Whether search terms or “keywords” will yield the information sought is a complicated question involving the interplay, at least, of the sciences of computer technology, statistics and linguistics …

United States v O’Keefe, 537 F. Supp. 2d 14, 24 (D.D.C. 2008)(Facciola, J.); See also Equity Analytics, LLC v. Lundin, 248 F.R.D. 331, 333 (D.D.C. 2008)(Facciola, J.).

The Gold Standard?

Human Review

“The idea that exhaustive manual review is the most effective—and therefore the most defensible—approach to document review is strongly refuted. Technology assisted review can (and does) yield more accurate results than exhaustive manual review, with much lower effort.”

Maura Grossman and Gordon Cormack, Technology-Assisted Review in E-Discovery Can Be More Effective and More Efficient than Exhaustive Manual Review, Richmond Journal of Law and Tech, Vol XVII, Issue 3 (2011).

Not Really...

Reality

Danziger, Leva and Avnaim-Pesso, Extraneous factors in judicial decisions, PNAS (2011).

Physiological Factors

“Justice is what the judge ate for breakfast” – Jerome Frank

Review accuracy may be what the junior associates ate for lunch

Executive function influenced by blood glucose levels, breaks, positive mood, and viewing pictures of nature.

What is Technology Assisted Review?

“By computer-assisted coding, I mean tools that use sophisticated algorithms to enable the computer to determine relevance, based on interaction with a human reviewer.”

Da Silva Moore v. Publicis Groupe (S.D.N.Y. 2012)

What Goes on Under the Hood? The computer builds a big, complex search!

What terms are most likely to be associated with good documents?

What terms are most likely to be associated with bad documents?

What is Computer Assisted Coding? By computer-assisted coding, I mean tools that

use sophisticated algorithms to enable the computer to determine relevance, based on

interaction with a human reviewer.

Da Silva Moore v. Publicis Groupe (S.D.N.Y. 2012)

It’s About Mathematics Support Vector Machines

Naïve Bayes

K-Nearest Neighbor

Geospatial Predictive Modeling

Latent Semantic

“I may be less interested in the science behind the ‘black box’ than in whether it produced responsive documents with reasonably high recall and high precision.”

– Peck, M.J. (SDNY)

Corporate e-discovery landscape

Lessons from Larger Corporations

Responding to the big data challenge

Increasing number and size of discovery events

Corporations taking control of discovery spend

Decreasing number of providers/firms across limitation portfolio

Fixed fee models

Managed service models

Greater diversity and overlap between corporate and cloud data sources

Changing approach to e-discovery

Lessons from Larger Corporations

Matter-based approach Each goes through EDRM model independently Reactive and linear process Fire-and-forget budgets

Manage entire discovery process as a proactive, unified, interactive, iterative lifecycle

Traditional:

Emerging:

Controlling litigation spending

Industry Overview

Centralized cross-functional environment Manage global collections and cases Single-instance storage Reduce and reuse Predictive analytics Technology-assisted review Intelligent synchronization and feedback

Control of data, reduced cost and risk

Business Benefits

One-time processing

Single-instance savings and efficiency

Leverage prior work-product for review and quality control

Get new matters started quickly — turnkey design

Cross-matter standardization

Retain document history

Key Points Effective use of all available technologies is crucial

Tools should be combined and workflows adjusted depending on what you’re trying to accomplish

You don’t have to be an expert to succeed with e-discovery

Mark Noel

Questions?

Shawn Cheadle

Managing Director, Professional Services Catalyst Repository Systems [email protected]

General Counsel Military Space, Lockheed Martin Space Systems Co. [email protected]