27
Technology Assisted Review Moving Beyond the First Generation John Tredennick CEO/Founder Catalyst

Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

Embed Size (px)

DESCRIPTION

Once a controversial tool in electronic discovery, technology assisted review (TAR), also known as predictive coding or computer assisted review, has gained judicial acceptance and is increasingly used for for document review in large-scale legal matters. Less recognized, however, is that TAR has a range of uses beyond simple review that can help in mastering large document sets, from information governance to early case assessment and preparing for depositions and trial. This presentation is by John Tredennick, Esq., CEO and founder of Catalyst Repository Systems. It covers how TAR works and the various ways lawyers are now using it.

Citation preview

Page 1: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

Technology Assisted Review Moving Beyond the First Generation

John Tredennick CEO/Founder

Catalyst

Page 2: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review
Page 3: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

§  1,800 Exabytes

§  1.8 million Petabytes

§  1.8 billion Terabytes

§  1.8 trillion Gigabytes

§  1.8 quadrillion Megabytes

1.8 Zettabytes a year

Library of Congress—30 Terabytes

Exploding Content >> Big Data

Sixty Million Libraries of Congress each year!

Page 4: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

60 million libraries a year...

... and growing

Page 5: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

0"

50"

100"

150"

200"

250"

300"

2003" 2004" 2005" 2006" 2007" 2008" 2009" 2010" 2011" 2012"

Case Size (in Gigabytes)

Big Data >> Big Discovery

Page 6: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

Telling Stories 1.  Your job has not changed. 2.  But it has gotten a bit harder. . .

þ  Find the story

þ  Tell the story

þ  Prove the story

Page 7: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review
Page 8: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review
Page 9: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

Trust

Page 10: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review
Page 11: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

Is This New?

Page 12: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

We Already Use It

Page 13: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

Predictive Ranking

Page 14: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

What is the Process? 1.  Assemble your files

Page 15: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

Shredding the Documents

1 2

3

Page 16: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

What is the Process? 1.  Assemble your files 2.  Add seed documents to the mix 3.  Analyze seeds and rank similar

documents

Page 17: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

How Does it Work?

Page 18: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

How Does it Work?

§  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)

Page 19: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

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?

Page 20: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

What is the Process? 1.  Assemble your files 2.  Add seed documents to the mix 3.  Analyze seeds and rank similar

documents 4.  Test results and provide more

samples—iterative process 5.  Order review by ranking

Page 21: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

Cut Point

Ranking a Document Set

Page 22: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

Understanding the Savings

0%#

10%#

20%#

30%#

40%#

50%#

60%#

70%#

80%#

90%#

100%#

0%# 10%# 20%# 30%# 40%# 50%# 60%# 70%# 80%# 90%# 100%#

Percen

tage)of

)Rele

vant)Docum

ents)Foun

d)(Re

call))

Percentage)of)Documents)Reviewed)

Yield)Curve)

Percentage of relevant documents found

Number of documents in the review

Linear Review

Page 23: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

0%#

10%#

20%#

30%#

40%#

50%#

60%#

70%#

80%#

90%#

100%#

0%# 10%# 20%# 30%# 40%# 50%# 60%# 70%# 80%# 90%# 100%#

Yield&Curve&

%&of&Documents&

%&Re

levan

t&

Review 12% and get 80% recall

Understanding the Savings

Page 24: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

0%#

10%#

20%#

30%#

40%#

50%#

60%#

70%#

80%#

90%#

100%#

0%# 10%# 20%# 30%# 40%# 50%# 60%# 70%# 80%# 90%# 100%#

Yield&Curve&

%&of&Documents&

%&Re

levan

t&

Review 25% and get 95% recall

Understanding the Savings

Page 25: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

12,000

10,000

8,000

6,000

4,000

2,000

Res

pons

ive

10,000 20,000 30,000 40,000 50,000 60,000 70,000 80,000 90,000

Reviewed

Wellington F Responsive Review

80% Recall Review 29,248

95% Recall Review 39,132

100% (Linear) Review 85,725

Page 26: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

12,000

10,000

8,000

6,000

4,000

2,000

Res

pons

ive

10,000 20,000 30,000 40,000 50,000 60,000 70,000 80,000 90,000

Reviewed

Wellington F Responsive Review

80% Recall Review 29,248

95% Recall Review 39,132

100% (Linear) Review 85,725

Predict(Review 80%(Recall 95%(RecallResponsive 9,168 10,887Reviewed 29,248 39,112Reduction 56,477 46,613Saving<($4<Doc) $225,908< $186,452<

Page 27: Technology Assisted Review: Moving Beyond the First Generation of E-Discovery Review

1.  You only get one bite at the apple.

2.  Subject matter experts are required for training.

3.  You must train on randomly selected documents.

4.  You can’t start TAR training until you have all of your documents.

5.  TAR doesn’t work on foreign (Asian) language documents.

6.  TAR doesn’t work with sparse collections.

The Five Myths of TAR