To get a comprehensive update
on predictive coding watch this on - demand webcast with predictive coding expert Ralph Losey, Predictive Coding 3.0.
A new post spotlights key details
on the predictive coding jurisprudence from 2016.
In 2014, experts and vendors were still pumping out webinars
on predictive coding, information governance and social media discovery.
Atlanta partner and E-Discovery Practice Leader Ronni Solomon, Discovery Center senior staff attorneys Ed Logan and Jennifer Mencken, and Discovery Center Director of e-Discovery Project Management and Client Services Rose Jones have co-authored a chapter in the book «Perspectives
on Predictive Coding and Other Advanced Search Methods for the Legal Practitioner,» published by the American Bar Association.
This book provides a set of perspectives
on predictive coding and other advanced search techniques, as they are used today by lawyers in pursuit of e-discovery, in investigations, and in other legal contexts, such as information governance.
Interestingly, although the case comes just less than a year after U.S. Judge Peck's latest opinion
on predictive coding in Rio Tinto Plc v. Vale S.A., it provides no reference to that ruling.
For more
on predictive coding, see the October 2010 eDiscovery Institute Survey
on Predictive Coding (PDF) and my colleague Foster Gibbon's July 2010 Integreon blog post, The Future of Automated Document Review.
I disagree with the conclusions
on predictive coding.
There was a big focus in the last year
on predictive coding solutions, social media, mobile devices, and the upcoming Federal Rules of Civil Procedure (FCRP) amendments.
Recent cases that demonstrate varying judicial perspectives
on predictive coding's role in e-discovery
In eDiscovery, discussions about «artificial intelligence» generally focus
on predictive coding — the machine learning process that reduces the time human reviewers must spend reading non-relevant information — by teaching the software to analyse periodic human feedback, learn for itself what information reviewers are actually interested in, and then locate that information.
From discussions
on predictive coding workflow, to collaboration and streamlined processes, respondents explicitly asserted the need for high - quality third party professionals.
There was a big focus in the last year
on predictive coding solutions, social media,...
In the survey, the most commonly cited reasons for not adopting it, among those familiar with their company's stance
on predictive coding, were: concerns about accuracy (62 per cent); difficult to defend (57 per cent); cost (57 per cent); concerns about privilege / confidentiality (54 per cent), and difficult to understand (53 per cent).
What are your thoughts
on predictive coding?
We recently posted insights from Melbourne - based FTI Technology director Phil Smith
on predictive coding adoption in Australia.
Well worth your time to read because many of the basic questions
on predictive coding have already been asked and answered.
Paul is a PhD - qualified mathematician with more than a decade of commercial software development experience and has provided expert witness testimony
on predictive coding methodology.
The DNNs are based
on predictive coding theory, which assumes that the internal models of the brain predict the visual world at all times and that errors between the prediction and the actual sensory input further refine the internal models.
Not exact matches
Once
code is set up to port data within a
predictive model, one can also automate that model's visualization and capitalize
on it as a moneymaker.
These variables are an important reminder as to why it is critical that clients beginning to leverage
predictive coding work with experts to advise
on which methods make the most sense for a matter's unique needs.
Likewise, for cases that involve a mix of hard copy documents and electronic documents, it is better to deal with the hard copy documents manually, and use some form of
predictive coding on the electronic documents to balance the manual work with a highly efficient approach for the digital portion.
On a practical level, Vogl pointed out that many law firms are working with vendors using machine learning and
predictive coding for e-discovery.
In Hyles v. New York City, 2016 WL 4077114 (S.D.N.Y. Aug. 1, 2016), Judge Peck wrote
on an issue that has become his trademark - the use of
predictive coding in e-discovery.
Judge Peck has released well - known decisions
on the topic, including Da Silva Moore v. Publicis Groupe, 287 F.R.D. 182 (S.D.N.Y. 2012) and Rio Tinto PLC v. Vale S.A., 306 F.R.D. 125 (S.D.N.Y. 2015), and has been a vocal advocate of expanding the use of
predictive coding.
So, picking up
on the ECA and
predictive coding themes, I don't think technology will eliminate review lawyers.
But one other relatively new development has an even more direct affect
on the contract attorney market and we have discussed it many times: the rapid move toward
predictive coding technology and machine review.
I'm going to quickly touch
on some key components of using technology - assisted review, or TAR, or
predictive coding in some of the interfaces that you may see in your products that you're using today.
I'm currently working
on a large matter in Australia that involves testifying to how the
predictive coding was applied and the validity of the results.
And most lawyers will still want to vet
predictive coding with humans, at least
on a sampling basis.
Progressing from screening for keyword to
predictive coding in which algorithms use
predictive analytics to determine the most relevant documents based
on search
As NSU explains, «This course provides hands -
on experience for students
on a number of key operational aspects of the practice of law, including the business foundation of successful law firm management; security and confidentiality of client information; marketing, public relations, advertising and social media; duties of technological competence under ABA «Ethics 20/20» amendments to the Model Rules of Professional Responsibility;
predictive coding and other eDiscovery issues; client intake and case management; and issues related to the scope and composition of representation, including the unauthorized practice of law and unbundled legal services.»
On the D4 blog and other blogs penned by experts in the e-discovery and litigation support fields,
predictive coding, TAR, CAR — all powered by
predictive analytics — has gotten tremendous coverage, especially over the last year.
Pursuant to the legal authorities which I have cited supra, and with particular reference to the albeit limited Irish jurisprudence
on the topic, I am satisfied that, provided the process has sufficient transparency, Technology Assisted Review using
predictive coding discharges a party's discovery obligations under Order 31, rule 12.
It was an informative gathering with lively roundtable discussions amongst peers
on interesting e-discovery topics such as: judges ordering the use of
predictive coding, indexing data by concepts, the practicality of co-operation and disclosure of
predictive coding to opposing counsel, whether it's possible to conduct privilege reviews using
predictive coding and even securing executive buy - in for «spring cleaning» data remediation projects.
Clients benefit from efficient e-discovery services; saving costs
on large, complex litigation cases by using
predictive coding.
- 31) 5.2 Introduction 5.3 Market Segmentation 5.3.1 By Solution 5.3.2 By Deployment Type 5.3.3 By Service Type 5.3.4 By Vertical 5.3.5 By Region 5.4 Evolution 5.5 Market Dynamics 5.5.1 Drivers 5.5.1.1 Focus
on Decreasing Operational Budget of Legal DEPArtments 5.5.1.2 Global Increase in Litigations 5.5.1.3 Stringent Policy and Compliance Regulations Worldwide 5.5.1.4 Increase in Mobile Device Penetration and Usage 5.5.2 Restraints 5.5.2.1 High Cost Associated With E-Discovery Solutions and Services 5.5.2.2 Contradiction Between Data Protection and E-Discovery 5.5.3 Opportunities 5.5.3.1 Rise in Demand for
Predictive Coding 5.5.3.2 Increased Usage of Social Media Websites 5.5.4 Challenges 5.5.4.1 Less Awareness About E-Discovery 5.5.4.2 Increase in Cross-Border E-Discovery
In litigation, Nelson explains that
predictive coding technology can be used to rank and then «
code» or «tag» electronic documents based
on criteria such as «relevance» and «privilege» to help reduce time spent
on page - by - page lawyer document review.
His primary focus in recent months has been
on the UX for Lexis DiscoveryIQ, a new eDiscovery enterprise software platform from LexisNexis that reimagines how and when
predictive coding is used in the workflow.
It sought advice from lawyer and e-discovery expert Conor Crowley, who suggested that using
predictive coding on the documents would be more effective and efficient.
Case study examples of
predictive coding and analytics working together
on a Second Request, internal investigation and for trial prep
In this ideal, corporations could conduct
predictive coding in a defensible manner, reduce the costs of e-discovery while keeping internal control of the process, and rely
on a service provider partner to constantly innovate
on the technology.
Ari: [29:16] Joe,
on that point, it was interesting, when we were doing the research, that 88 percent of the people, both in - house counsels and law firm lawyers, wanted to learn more about measuring and understanding the effectiveness of
predictive coding.
And that's before we start to venture into the territory of the top end of eDiscovery software and the vendors supplying
predictive coding systems based
on NLP and machine learning.
With the emergence, and apparent judicial acceptance, of
predictive coding and the certainty of greater technological advancements
on the horizon, attorneys will be well - served to understand and embrace these changes as they come.
Predictive Analytics (also called «
Predictive Coding» or «Technology Assisted Review») is a workflow that requires a subject matter expert to review a small subset of documents in order to train the system
on what the human is looking for until the system can statistically «predict» how the human would
code the rest of the collection.
Predictive coding continues to make inroads in eDiscovery demonstrating that software analysis is more accurate and faster that hordes of associate lawyers clicking
on documents
on screens.
Additionally, since the
predictive coding program relies
on the judgment of the senior attorney who trains it, the outcomes are likely to be more consistent and accurate than if an attorney hires multiple individuals who are less familiar with the facts to review the documents.
With
predictive -
coding, the software delivers results based
on keywords that are set by seasoned attorneys, and then the software can be tweaked to improve accuracy over time.
[5] Ralph Losey, ibid., at 25, states that
predictive coding (a variety of TAR) was slow to be used by U.S. lawyers until the decision of Magistrate Judge Andrew J. Peck
on Feb. 24, 2012, in, Da Silva Moore v. Publicis Groupe 287 F.R.D. 182 (S.D.N.Y. 2012), approving the use of
predictive coding, listing justifications.