Analytics & Predictive Coding:Changing the Landscape for Investigations & eDiscovery
Beth Patterson - Applied Legal Technology Director, AllensJonathan Wong - Associate Freshfields Bruckhaus Deringer
Akiko Miyake – Director, FTI
3 March 2014
Overview
• Why Analytics & Predictive Coding Matter
• Defining Analytics & Predictive Coding
• What is the uptake: Asia? Worldwide?
• Deciding on what to use & why: It’s not either/or
• Case Studies
• Key Takeaways
Why Analytics & Predictive Coding Matter
Disruptive Technologies: Advances that will transform life, business, and the global economy McKinsey Global Institute May 2013
Why Analytics & Predictive Coding Matter
Disruptive Technologies: Advances that will transform life, business, and the global economy McKinsey Global Institute May 2013
Defining eDiscovery Analytics
• Analyze information: how are documents distributed based on custodians, date ranges, keywords and other critical factors
• Concept clustering: visualizations of large data sets using concepts
• Review prioritization: prioritization of specific documents
• Reporting: monitor review across a variety of metrics, real-time reporting
Defining Predictive Coding
“E-discovery Taking Predictive Coding Out of the Black Box”, FTI Journal, Nov 2012
Predictive Coding eDJ Group 2013 Asian eDiscovery Survey
Predictive Coding eDJ Group 2013 Asian eDiscovery Survey Results
Predictive Coding eDJ Group 2013 Asian eDiscovery Survey Results
Discussion & Case Studies
Case Study Analytics Review Prioritisation
90-100 80-90 70-80 60-70 50-60 40-50 30-40 20-30 10-20 0-100%
10%
20%
30%
40%
50%
60%
70%
80%
90%
100%
Proportion of Relevant/Non-Relevant Documents in each Con-fidence Level
Non Relevant Relevant
Analytics Confidence Level
Prop
ortio
n of
Doc
umen
ts
Key Takeaways
Akiko Miyake – Director, FTI
Jonathan Wong - Associate Freshfields Bruckhaus Deringer
Beth Patterson - Applied Legal Technology Director, Allens