All posts tagged predictive coding

Spring Digest: Everything You Need to Know (so far!) in 2017

Ediscovery has been busy this year. We’re only five months in and we’ve already seen developments in predictive coding, proportionality standards and ediscovery practices around the world.

Before you head off on your summer vacation, take a minute to refresh yourself on some of the hottest topics in ediscovery so far this year.

Proportionality is Key

One of the most significant amendments to the Federal Rules of Civil Procedure back in 2015 was a new requirement for discovery to be “proportional to the needs of the case.” Today, counsel must ensure that their discovery requests are specific and add value to their case in relation to the accompanying expense.

Australia Gets in the Predictive Coding Game

First the United States, then Ireland and England, and now Australia. Predictive coding (also known as TAR) continues to spread around the world as courts encourage parties to consider technology to discover and inspect documents.

Using Cellebrite in Mobile Phone Investigations

You need not be a computer wizard to appreciate the volumes of relevant data housed on the mobile device in your hand. The standards and technology for extracting mobile device data are still progressing, variable and slightly confusing. KrolLDiscovery’s Jason Bergerson answers common questions around specific technology and processes in mobile phone investigations.

Ediscovery Around the World

Throughout this year, KrolLDiscovery will be diving deep into ediscovery practices around the world. We hope you’ll join us as we explore data collection, privacy, proportionality and production practices in the Americas, EMEA and APAC. So far, we’ve stopped in Australia, Ireland, Canada, the U.K. and Germany to discuss some ediscovery trends in each locale.

Be sure to sign up for updates from The Ediscovery Blog to stay on top of everything ediscovery.

The Results are In: Sixth Annual Best of the National Law Journal Survey

“We are honored to be chosen as a leading ediscovery provider in so many service and technology categories by National Law Journal readers.” Chris Weiler, CEO of KrolLDiscovery.

For the last six years, the National Law Journal (NLJ) has conducted a survey asking its readers to rank top providers in the legal marketplace. From data, research and technology to finance, expert witness and outsourced services, this survey highlights the businesses and individuals seen as the best in the industry. In all, the legal community cast over 4,500 votes to select the 2017 Best of The National Law Journal winners.

Given the collective opinions of thousands and the esteem of this national survey, KrolLDiscovery is honored to receive 10 awards, including four top honors, in this year’s survey. Specifically, KrolLDiscovery took home the gold award in the following categories:

  • Managed Ediscovery & Litigation Support Service Provider
  • Managed Document Review Services
  • Predictive Coding Ediscovery Solution
  • Data Recovery Solution Provider

Additionally, the company received silver awards in four categories:

  • End-to-End Litigation Consulting Firm
  • Technology Assisted Review Ediscovery Solution
  • Data & Technology Management Ediscovery Provider
  • Online Review Platform

Third-place honors include:

  • End-to-End Ediscovery Provider
  • Case Management Software to Law Firms

It’s great to know that all of the hard work of LDiscovery and Kroll Ontrack – now together as KrolLDiscovery – was recognized by NLJ readers. Learn more about all of KrolLDiscovery’s innovative technology and best-in-class services to support litigation, investigation, compliance and recovery from data loss. And, thanks to everyone that voted!

The Luck of the Irish…and Predictive Coding

On this St. Patrick’s Day, it’s opportune to revisit a prominent Irish judicial opinion – in fact, the first known judicial opinion in Europe to endorse predictive coding.

In the spring of 2015, Ireland embraced predictive coding in Irish Bank Resolution Corporation Ltd v. Quinn [2015] IEHC 175, a case holding that, in the discovery of large data sets, technology assisted review (TAR) using predictive coding is at least as accurate as, and probably more accurate than, the manual or linear method of identifying relevant documents.

The judgment is a great read for predictive coding pundits and a shining endorsement of the potential benefits of this technology. Specifically, the court held that:

  • The rules of court in Ireland do not require a manual document review to be carried out;
  • The evidence establishes that in discovery of large data sets, TAR using predictive coding is at least as accurate as, and probably more accurate than, the manual or linear method in identifying relevant documents;
  • As TAR combines man and machine, the process must contain appropriate checks and balances which render each stage capable of independent verification. The parties need to agree to these;
  • Provided the process has sufficient transparency, TAR using predictive coding discharges a party’s discovery obligations;
  • Predictive coding will save time and money if used to refine a data set and to limit the pool of documents to be manually reviewed. It was projected that 10% of the 680,809 documents would need to be manually reviewed after employing predictive coding, as compared to the traditional linear review estimate that required a team of 10 experienced reviewers, a nine month time frame and a cost of two million Euros; and
  • Parties should first agree to the use of predictive coding, run agreed upon keyword searches to initially refine the data set and then use predictive coding subject to agreed-upon checks and balances. Documents suggested by the software as being potentially relevant should then be reviewed manually by a human review team.

The ruling addressed major concerns expressed about predictive coding and sought to sway the skeptics. It unequivocally stated that predictive coding will save time and money. Although there is no specific reference to proportionality in Irish law, the judgment stated that cost should not be a barrier on access to justice.

The Irish opinion relied significantly on Judge Peck’s Da Silva Moore opinion, setting the predictive coding tone in the United States in 2012. A year after Ireland’s Quinn opinion, the UK would celebrate its first judicial opinion referencing predictive coding when the English High Court issued Pyrrho Investments Ltd. v. MWB Property Ltd. [2016] EWHC 256 (Ch). In that case, Master Matthews estimated that predictive coding would offer significant cost savings and that the possible disclosure of over two million documents done via traditional manual review would be disproportionate and “unreasonable.” Late in 2016, Australia joined the list of countries tackling predictive coding issues when Justice Vickery from the Supreme Court of the State of Victoria issued a key opinion in McConnell Dowell Constructors v. Santam.

As we continue through 2017, what country will be next to focus on predictive coding? Don’t miss any development; subscribe to KrolLDiscovery’s weekly email updates.

Australia Gets in the Predictive Coding Game

G’day, mate!

As we have said before, predictive coding (also known as Technology Assisted Review or TAR) is taking the globe by storm. First the United States, then Ireland and England, and now Australia. Ediscovery practitioners take heed: significant predictive coding developments are afoot in Australia.

(Special Note: If you are looking to stay informed on ediscovery around the world, don’t miss this whitepaper, “A Practical Guide to Cross-Border Ediscovery.”)

Predictive Coding: From New York City to the Australian Outback

Late last year, Australia joined the list of countries tackling predictive coding issues when Justice Vickery from the Supreme Court of the State of Victoria issued a key opinion in McConnell Dowell Constructors v. Santam.

In this case, the parties faced massive costs to review 1,400,000 documents, and they could not agree on a review method. Justice Vickery appointed a Special Referee to deliver a report to the court addressing the appropriate management of discovery in the proceeding. Relying on previous TAR decisions from the U.S. and Europe, as well as the Special Referee’s recommendation to use TAR, the court approved predictive coding as an effective method of document review when “the cost of traditional discovery processes in a case such as this dictates that [such processes] are not appropriate.”

Notably, the McConnell opinion made it clear that the courts, not the parties, would have the final determination in whether predictive coding will be employed in civil proceedings in Victoria state court. Specifically, Justice Vickery held that “the Court may order discovery by technology assisted review, whether or not it is consented to by the parties” in cases where the volume of ESI is substantial and “the costs of research may not be reasonable and proportionate.”

However, McConnell was not Victorian litigators’ first exposure to TAR in the courtroom. Three months before the McConnell decision, the Supreme Court of Victoria released a Standard Operating Procedure (TEC SOP 5 [TAR]) to provide litigants with interim measures for using TAR in construction and engineering cases. On January 30, 2017, the court replaced TEC SOP 5 with Technology in Civil Litigation Practice Note SC Gen 5, opening up TAR for general use in Victoria’s commercial courts.

Consent or No Consent: That is the Predictive Coding Question

While predictive coding is gaining traction as an effective tool to tackle massive document sets, there is no bright line on whether a party can be required to use TAR. Contrary to the holding in McConnell, U.S. courts have not compelled parties to leverage TAR. In 2016, two key opinions, Hyles v. New York City, 2016 U.S. Dist. LEXIS 100390 (S.D.N.Y. Aug. 1, 2016), and In re Viagra (Sildenafil Citrate) Prods. Liab. Litig., 2016 BL 347130 (N.D. Cal. Oct. 14, 2016), acknowledged the efficiencies associated with predictive coding, but refused to force a party to leverage the cutting-edge technology. That being said, U.S. attorneys need to be prepared that the days of insisting on manual review may one day soon be bygone. As noted by Judge Peck in Hyles, “[t]here may come a time when . . . it might be unreasonable for a party to refuse to use TAR . . . [but][w]e are not there yet.”

What’s Next for the Land Down Under?

Victoria is not the only state in Australia getting in on the ediscovery action. Courts in New South Wales abide by their state Supreme Court’s 2008 Practice Note No. SC Gen & for Use of Technology encouraging parties to consider technology to discover and inspect documents. While this practice note and other similar guidance in the Australian federal court system do not specifically reference TAR, savvy Australian practitioners know that this will likely change in the near future.

Looking to stay up to speed on global ediscovery practices? Don’t miss this whitepaper, “A Practical Guide to Cross-Border Ediscovery.”

Looking Back, Peering Forward: The Top Ediscovery Cases of 2016

The 2015 FRCP amendments are now one year old and there are a full twelve months of case law to guide practitioners through the contours of the new rules. The last year in case law has seen stark developments on how courts interpret the proportionality, levy sanctions, utilize new technologies and reconsider costs to make ediscovery “just, speedy and inexpensive.”

Our webinar, The Top Ediscovery Cases of 2016, updates practitioners on the ediscovery highlights of the past year and features three ediscovery experts, offering the perspective of both counsel and judges:

  • Patrick Oot, Shook, Hardy & Bacon
  • Magistrate Judge Hildy Bowbeer, District of Minnesota
  • Magistrate Judge David J. Waxse, District of Kansas

Rule 26(b)(1): Proportionality Today

The webinar first discusses that the most drastic change of Rule 26(b)(1) is the essential change of mindset. The case Gilead Scis. v. Merck is used as an example to illustrate the place of proportionality in ediscovery. Gilead reveals the required sound reasoning both a party requesting discovery and a party objecting to discovery need to employ. In other words, “now the scope of discovery is neither broad nor liberal…it is proportional.” Attorneys that ignore proportionality do so at their own risk: the case Fulton v. Livingston Fin. is also used to show how the court imposed sanctions on a litigant who made arguments based on the old rule.

Rule 37(e): Sanctions Illustrated

The webinar then discusses the scope of Rule 37(e) and addresses the need to utilize “reasonable steps” to prevent sanctions, as this rule was formed with the intent of curtailing excessive ESI storage. The webinar uses the case Marten Transp. v. Plattform Adver. to show that the scope of a preservation duty is focused: courts expect “reasonable steps,” not perfection. The case Living Color is also used to highlight the fact that parties cannot simply make conclusory statements about prejudice resulting from ESI spoliation without any evidence and expect the court to levy sanctions.

One reason for excessive ediscovery costs is a cultural one and the webinar highlights that Rule 37(e) fits with Rule 1, which was amended for this reason. Cooperation between litigants is a key component of successful preservation, and a panelist observed, “Lawyers too often ignore their obligation to cooperate.”

Predictive Coding: New Frontiers

There are two myths underlying document review discussed in the webinar. The first is the myth that a response to discovery needs to be perfect when in fact the rules call only for “reasonable inquiry.” The second myth is that human review is the best way to ensure responsive documents are not missed when manual review has been shown to be imperfect. In this webinar, the discussion of these two myths sets the stage for asserting that predictive coding technology can be utilized to make ediscovery a more efficient practice.

2017: The Year of Ediscovery

In 2017, one common wish is that attorneys become better educated in ediscovery and the new technologies available. Courts will continue to dissect what constitutes reasonable steps for ESI preservation and also provide additional guidance for when discovery is proportional. Even though counsel may not be proficient in proportionality, the webinar concludes by stating that judges “recognize proportionality when they see it.”

With new opinions continuing to emerge, we expect the ediscovery landscape in 2017 to continue to evolve. Watch this webinar, The Top Ediscovery Cases of 2016, to learn more about the impact of the 2015 FRCP amendments and predictions for the upcoming year.

DOJ ANTITRUST DIVISION ISSUES NEW MODEL SECOND REQUEST, WITH NEW PREDICTIVE CODING INSTRUCTIONS

On November 28, 2016, the Department of Justice (DOJ) Antitrust Division issued an updated Model Second Request, aimed at revising and streamlining the model to conform to “current division practice.” The updated Model will be used for all Second Requests issued on or after December 12, 2016. The new model contains significant changes to merging parties’ obligations during a Second Request, as well as a substantial formatting overhaul.

Regarding the use of ediscovery technology during a Second Request from the DOJ, the predictive coding instructions were meaningfully modified.

First, the new model appears to signal an increased acceptance of use of predictive coding during a second request. Specifically, the searching and predictive coding instruction begins with the following new language, “Before using software or technology…” seemingly indicating that the Antitrust Division recognizes that it is not a matter of “if” parties are leveraging technology but “when” and “how” that technology will be used.

Second, the new model requires merging parties and their counsel to be more astute than ever before when it comes to ediscovery technology. For example, if search terms are used, merging parties must now submit a list of stop words and operators for the platform being used. Also, if predictive coding technology is used to identify or eliminate documents, merging parties must provide more than just a description of the methods being used. Under this new model, the Antitrust Division also is requiring information about the use of subject matter experts to review seed sets and training documents, effectiveness metrics (such as recall, precision and confidence-intervals) and validation protocols, including sampling protocols used to categorize non-responsive documents.

The new predictive coding and searching instruction is provided in full below:

November 2016 Version – DOJ Model Second Request

  1. Before using software or technology (including search terms, predictive coding, de-duplication, or similar technologies) to identify or eliminate documents, data, or information potentially responsive to this Request, the Company must submit a written description of the method(s) used to conduct any part of its search. In addition, for any process that relies on search terms to identify or eliminate documents, the Company must submit: (a) a list of proposed terms; (b) a tally of all the terms that appear in the collection and the frequency of each term; (c) a list of stop words and operators for the platform being used; and (d) a glossary of industry and company terminology. For any process that instead relies on predictive coding to identify or eliminate documents, you must include (a) confirmation that subject-matter experts will be reviewing the seed set and training rounds; (b) recall, precision, and confidence-level statistics (or an equivalent); and (c) a validation process that allows for Department review of statistically-significant samples of documents categorized as non-responsive documents by the algorithm.

As these new instructions reinforce, Second Requests are synonymous with sheer complexity. At Kroll Ontrack, we have leading technology backed by human experts who know how to successfully navigate a Second Request. Kroll Ontrack is uniquely equipped to help manage your document productions to the FTC, DOJ and other global competition bureaus.

Global Predictive Coding: Gold, Silver & Bronze

This week, athletes from around the globe will gather in Rio to compete for gold medals and present years of hard work and dedication. With the Games as a backdrop, there is no better time than to explore our own global phenomenon in ediscovery – predictive coding technology.

Recently, Kroll Ontrack’s Michele Lange and Tracy Stretton co-authored an article for Bloomberg BNA’s Digital Discovery & e-Evidence in which they discussed the way predictive coding is taking the globe by storm.

A Global Predictive Coding Case Law Primer

Taking the gold medal for the first predictive coding judicial opinion, several years ago American courts approved the use of predictive coding technology in discovery, making it widely recognized and respected. In March 2015, Ireland earned the silver medal with its approval of the use of predictive coding in the discovery process in Irish Bank Resolution Corporation Ltd. & Ors v. Quinn & Ors. In February 2016, Master Matthews helped Britain win the bronze when he issued the first British opinion, known as Pyrrho Investments Ltd. v. MWB Property Ltd., which approved the use of predictive coding in High Court proceedings, partly relying on Magistrate Judge Peck’s opinion in Da Silva Moore v. Publicis Groupe. Even more recently in May 2016, Britain had its first contested case regarding predictive coding, David Brown v. BCA Trading. These opinions are just the start of what we will see on the issue of predictive coding in years to come. Case law will continue to develop as many of the same concerns are being raised globally.

What’s Next on the Horizon?

As discussed by Lange and Stretton in their article, in the US and UK, judges will continue to interpret the nuances of parties’ predictive coding practices and it will not be long until other European and Asian countries formally join the predictive coding games. In the meantime, technology is evolving so legal professionals must stay vigilant to meet the expectations of demanding international clients when producing electronic documents in global litigations or investigations.

Predictive Coding Technology: A Summer Blockbuster You Won’t Want to Miss

Predictive Coding Patent

What’s better than a summer blockbuster? Few things beat the heat better than an air-conditioned theater and a bucket of buttery popcorn while watching an engaging film.

Predictive Coding Patent Blockbuster:  Technology You Don’t Want to Miss

Kroll Ontrack has come out with its own “blockbuster” this summer: a predictive coding patent. Obtaining patents, like making blockbuster movies, takes years and ours was more than four years in the making. To accompany our patent, we have another mega-hit that deserves a second screening: Kroll Ontrack’s predictive coding guide. Our newly-patented technology, paired with our ever-relevant predictive coding guide, is a superhero team that the up-to-date ediscovery practitioner cannot do without.

2016 Summer Blockbusters: Movies You Don’t Want to Miss

Of course, there are other highly anticipated blockbusters arriving this summer. To start, the smart mouth turtles-turned-mutants of our youth are back in Teenage Mutant Ninja Turtles: Out of the Shadows. In Independence Day: Resurgence the people of earth once again are in critical struggle against an alien invader (hopefully with a better spaceship design). The daffy ghost hunters have returned in revival of the ’80’s classic movie Ghostbusters, this time with an all-female cast and the same catchy theme song. Star Trek Beyond continues the story of the USS Enterprise crew in the newest installment in one of popular culture’s longest-running franchises. Finally, the list would not be complete without the newest villain-themed movie from the Batman franchise: Suicide Squad.

Live Long and TAR!

UK High Court Approves the Use of Predictive Coding in Litigation

UK Predictive Coding

Legal technology providers in the UK have a lot to celebrate as the English High Court recently approved the use of predictive coding for disclosure in litigation.

The judgment, handed down by Master Matthews in Pyrrho Investments Ltd. v. MWB Property Ltd. [2016] EWHC 256 (Ch), gave official judicial authorization for the use of predictive coding in High Court proceedings. Summing up his decision, Master Matthews stated that predictive coding is just as accurate, if not more so than a manual review using keyword searches, mirroring the sentiments shared by Judge Peck’s 2012 opinion in Da Silva Moore v. Publicis Groupe regarding the appropriateness of predictive coding and its potential benefits. Master Matthews also estimated that predictive coding would offer significant cost savings in this particular case and that the possible disclosure of over two million documents done via traditional manual review would be disproportionate and “unreasonable.”

To read a short summary of the judgment, please click here, or read the judgment in full here.

Predictive Coding Goes Global

Predictive coding has become a global phenomenon over the past few years. The United States and Ireland have led the way in giving judicial approval to predictive coding, with Judge Peck’s Da Silva Moore opinion setting the predictive coding tone in 2012. Since then, the United States has continued to adopt the use of predictive coding, with a number of substantive cases further establishing its use. Ireland recently embraced predictive coding as well in the 2015 Irish Bank Resolution Corporation Ltd & ors v. Quinn & ors case holding that, in the discovery of large data sets, technology-assisted review using predictive coding is at least as accurate as, and probably more accurate than, the manual or linear method of identifying relevant documents. Not surprisingly, the Pyrrho judgment in the UK references these cases in detail.

Combatting Predictive Coding Objections

Despite these cases and the ever-increasing sophistication of the technology itself, the UK law community has been somewhat reluctant to make use of the technology, as explored in this study by Kroll Ontrack Legal Consultant and former litigation lawyer Hitesh Chowdhry. In Chowdhry’s white paper, “Rage against the Machine; Attitudes to Predictive Coding Amongst UK Lawyers,” he notes that his study revealed that the main barriers to adopting predictive coding technology were:

  • Risk aversion and mistrust of the technology’s accuracy
  • Belief that predictive coding would have a negative effect on revenue
  • Satisfaction with existing methods and a belief that existing practices offered more accuracy than studies have suggested
  • Insufficient understanding and knowledge of the complex predictive coding process
  • Diffusion among professionals

The UK Pyrrho judgment counters many of the fears uncovered in Chowdhry’s study by stating that the technology is accurate and offers cost savings. The efficiency of TAR and the cost savings offered by predictive coding will undoubtedly be popular with clients and potentially will give a competitive edge in winning work. Hopefully, this ruling will encourage more UK firms to take advantage of the benefits offered by predictive coding.

For more information about this technology, read Kroll Ontrack’s e-book, “Mastering Predictive Coding: The Ultimate Guide.”

Never Second Guess a Second Request

Second Request

Massive mergers are never a simple matter for organizations and their antitrust attorneys. The Second Request process can be a major burden for merging organizations since it requires that companies review, analyze and produce massive volumes of data in what can be a very short amount of time. If that doesn’t already cause panic, keep in mind that failing to fully comply can lead to substantial civil penalties and even the rejection of the merger transaction.

While Second Requests are a daunting task for any antitrust lawyer, my colleagues John D. Pilznienski and Sheldon A. Noel recently discussed the requirements counsel must meet to comply with a Second Request and how utilizing analytics like predictive coding can help simplify the process. The article written by Pilznienski and Noel, “Never Second Guess a Second Request: Leveraging Predictive Coding for Reviewing Documents in Antitrust Matters,” appeared in the March 2016 edition of Digital Discovery & e-Evidence, a Bloomberg BNA publication.

Read the article: Never Second Guess a Second Request

What is a Second Request?

For those of you not intimately aware of the corporate merger process, a Second Request is the issuance of a request by the Department of Justice (DOJ) or Federal Trade Commission (FTC) for “additional information and documentary material relevant to the proposed acquisition.” When corporations intending to merge meet a certain financial threshold, their proposed merger is subject to review by federal antitrust agencies. If the DOJ or FTC determines that more information is needed to ensure that there is no violation of federal antitrust laws during the initial review, they can request more information from the merging corporations. These requests can be extremely broad, requiring extensive resources, time and manpower to collect, process and produce the relevant documents and data.

Second Requests, Ediscovery and Predictive Coding: A Case Study

As discussed in the article by Pilznienski and Noel, in a recent technology sector merger the two companies utilized Kroll Ontrack’s predictive coding technology and review platform to respond to an FTC Second Request. The merger presented a number of hurdles – a large data set, multiple jurisdictions, complicated review guidance based on the document requests and an unexpectedly short production deadline – all of which were easily overcome by leveraging predictive coding. From the approximately 600,000 searchable documents, a random sample of approximately 2,300 documents was generated, sampled at a 95% confidence level and a 2% margin of error.  After applying a variety of review methods, the most relevant documents were reviewed first, aiding the merging companies in meeting the FTC’s deadline and significantly reducing the costs of review.

Be sure to read the full article, Never Second Guess a Second Request: Leveraging Predictive Coding for Reviewing Documents in Antitrust Matters, for a more in-depth discussion on the application of predictive coding to the Second Request process.

 
css.php