Insight Predict

  • 5 Myths About Technology Assisted Review

    Download 5 Myths copy

    By John Tredennick

    The world isn’t flat and we’ve stepped on the moon, so it’s not impossible to change our view about technology.

    There was a time when people believed the earth was flat. Or that humans would never walk on the moon. Or that computers had no place in the law. But then the non-believers proved them wrong. The earth is round, men have walked on the moon, and it is hard to imagine practicing law without a computer.

    There was a time when people believed the earth was flat. Or that humans would never walk on the moon. Or that computers had no place in the law. But then the non-believers proved them wrong. The earth is round, men have walked on the moon, and it is hard to imagine practicing law without a computer.

    Read Full Article >>


  • Ask Catalyst: A User's Guide to TAR

    Download TAR for Smart People

    Your Questions Answered About Technology Assisted Review

    By John Tredennick, Jeremy Pickens, Robert Ambrogi, Thomas C. Gricks III & Mark Noel

    At Catalyst, we receive many questions about technology assisted review and the workflows related to our advanced TAR 2.0 platform (Insight Predict) and its continuous learning algorithm. Other questions address generic TAR topics. Your questions were so good that we thought it would be useful to compile them and our answers into a book for handy reference. We hope you find it useful.

    Get Full E-Book >>




  • Contextual Diversity

    Continuous Active Exploration of Information

  • Continuous Active Learning for Technology Assisted Review

    Articles Download CALBy John Tredennick

    How It Works and Why It Matters for E-Discovery

    Peer-Reviewed Study Compares TAR Protocals

    Two of the leading experts on e-discovery, Maura R. Grossman and  Gordon V. Cormack, presented a 2014 peer-reviewed study on continuous active learning to the annual conference of the Special Interest Group on Information Retrieval, a part of the Association for Computing Machinery (ACM), “Evaluation of Machine-Learning Protocols for Technology-Assisted Review in Electronic Discovery.”

    In the study, they compared three TAR protocols, testing them across eight different cases. Two of the three protocols, Simple Passive Learning (SPL) and Simple Active Learning (SAL), are typically associated with early approaches to predictive coding, which we call TAR 1.0. The third, continuous active learning (CAL), is a central part of a newer approach to predictive coding, which we call TAR 2.0.

    Read Full Article >>

  • Insight for Investigations

    Download ProductGuide Forensics and Collections

    Powering Technology Assisted Compliance Worldwide

    When legal compliance is in question, no company can afford to delay or turn a blind eye. Companies should regularly monitor compliance and, when questions arise, respond quickly and thoroughly. Yet compliance often requires assembling and searching large quantities of data. Handling this manually takes time and drives up the cost and the risk of error. Using Insight for investigations provides a powerful set of user-driven technology tools that streamline and expedite internal corporate and government compliance investigations. This helps corporate counsel, compliance officers and government officials to respond to issues more effectively and efficiently.

    Read Full PDF >>

  • Insight Predict

    brochures catalyst predictive ranking download

    Predictive Ranking Streamlines Review

    From the first days of e-discovery, teams have reviewed documents in a linear fashion, jumping from relevant to irrelevant with no way to make the process more efficient. Now, using Predictive Ranking, we can separate the relevant documents in advance and dramatically reduce the need to review irrelevant documents. You save on review costs without sacrificing defensibility.

    How Predictive Ranking Works

    The process is simple. We start by sampling the initial collection. This might be millions of documents, most of them irrelevant. The sample is presented to a case expert on your team, who is asked to mark the documents responsive or non-responsive.

    As this initial process progresses, our computers watch and analyze the documents being tagged, determining what makes a document responsive or not. Using artificial intelligence techniques, our system develops searches that will identify each category of documents.

    Read Full PDF >>

  • Major Bank Slashes Review Costs with Innovative E-Discovery Technology

    Download Major Bank Slashes Review Costs with Innovative E-Discovery Technology

    Catalyst’s Insight Predict Cuts Production Review Costs by 94%

    Our client was a large banking institution embroiled in nasty litigation with a now-defunct borrower. The bank alleged it lost millions due to the borrower’s principals’ accounting fraud. Legal shots were fired, excuses ran rampant and the parties went hard at each other to see where the blame would end up. Bring on the discovery.

    Responding to a production request, our client conducted an extensive investigation to find responsive documents. Even after using a variety of techniques to cull those that it found, it was still left with over 2.1 million that needed consideration. Further keyword searching might have resulted in more reductions but the team wasn’t comfortable with what that process might miss.

    Read Full Case Study >>



  • Patent Case Proves It’s Never Too Late to Use TAR

    Download Patent Case Proves

    Even After Manually Reviewing Half the Collection, TAR Produced Substantial Savings

    “It’s never too late,” people often say. But is that true for technology assisted review? If a legal team has already put substantial time and effort into manual review, can TAR still be worthwhile? That was the issue presented in a patent infringement case where the client’s approval to use TAR came only after the law firm had manually reviewed nearly half the collection. Even that late in the game, Insight Predict produced substantial savings in time and cost.

    Read Full Case Study >>



  • Predict Proves Effective for Small Collection

    Download Predict Proves Effective for Small Collection

    Facing Tight Deadline in SEC Probe, Company Reduces Review by 75%

    The question has persisted since technology assisted review got its start. How big does a case need to be before it makes sense to load it into a TAR system? Is 10,000 documents enough? How about 100,000? In this case, it was just 16,000 documents, but TAR enabled the company to cut its review by 75% and get it done in under a week.

    Read Full Case Study >>



  • Predictive Coding Helps Companies Reduce Discovery Costs

    Download Predictive Coding

    By John Tredennick

    Attorneys have long felt it necessary to manually review each document being considered for production. When data volumes were still relatively small, this expense was a rounding error on much bigger legal budgets. However, as document volumes increased into the millions, attorney review costs mushroomed to become the largest part of the discovery spend.

    Faced with increasing volumes, corporate counsel began looking for new ways to cut review burdens. They began using search techniques designed to better target relevant documents and exclude junk. Then they employed clustering to help group documents with similar content. Some sent review work offshore. All the while, volumes kept increasing, outpacing counsel’s ability to keep up.

    Recently, a more-promising approach to reduce document volumes has emerged. Called variously predictive coding, computer-assisted review and technology-assisted review, the technology has been proven to streamline the review process dramatically, reducing both the quantity of data involved and the time required to sift through it.

    Read Full Article >>

  • Predictive Ranking: TAR Designed for the Real World

    Download Predictive Ranking

    By Jeremy Pickens

    Why Predictive Ranking?

    Most articles about technology assisted review (TAR) start with dire warnings about the explosion in electronic data. In most legal matters, however, the reality is that the quantity of data is big, but it is no explosion. The fact of the matter is that even a half million documents—a relatively small number in comparison to the “big data” of the web—pose a significant and serious challenge to a review team. That is a lot of documents and can cost a lot of money to review, especially if you have to go through them in a manual, linear fashion. Catalyst’s Predictive Ranking bypasses that linearity, helping you zero-in on the documents that matter most. But that is only part of what it does.

    In the real world of e-discovery search and review, the challenges lawyers face come not merely from the explosion of data, but also from the constraints imposed by rolling collection, immediate deadlines, and non-standardized (and at times confusing) validation procedures. Overcoming these challenges is as much about process and workflow as it is about the technology that can be specifically crafted to enable that workflow. For these real-world challenges, Catalyst’s Predictive Ranking provides solutions that no other TAR process can offer.

    Read Full Article >>


  • Regulatory Agency Cuts Review by 60%

    Insight Predict Helps a Small Team Meet a Tight Discovery Deadline

    Download Regulatory Agency Cuts Review by 60

    When the regulatory agency sued the private company, it sought to recover over $1 million the company had allegedly overbilled the government. But when the short-staffed agency faced a tight discovery deadline in the case, it knew there was not time for manual review. Turning to Insight Predict, Catalyst’s second-generation technology assisted review (TAR) platform, the agency was able to cut its review nearly 60%.

    Read Full Case Study >>

  • TAR Does Double Duty in a Government Probe

    Download TAR Does Double Duty

    Insight Predict Reduces Review and Rescues Privileged Documents

    In a highly sensitive government investigation, discovery is a delicate balancing act. You want to be sure to produce everything you are supposed to produce. But you just as surely want to steer clear of inadvertently producing privileged information. On both sides of this equation, technology assisted review (TAR) can provide greater certainty, while still reducing the overall time and cost of your review.

    This was demonstrated in a case involving a government investigation of a digital entertainment company. Using Insight Predict, Catalyst’s advanced TAR platform, the company’s legal team achieved two critical outcomes. First, even though they wanted eyes-on review of every document that might be produced, they still were able to stop after reviewing just 60% of the total population. Second, by using Predict as a preproduction check for privileged documents, they “rescued” several privileged documents that had been slated for production.

    Read Full Case Study >>

  • TAR for Smart People

    Download TAR for Smart People

    Expanded and Updated Seconded Edition

    How Technology Assisted Review Works & Why it Matters for Legal Professionals

    By John Tredennick, Mark Noel, Jeremy Pickens, Robert Ambrogi & Thomas C. Gricks III

    Technology Assisted Review has been a game changer for e-discovery professionals, offering dramatic savings in both time and review costs for savvy clients and their legal counsel. This book confronts the difficult issues with the first generation of TAR applications, while showcasing the newer, more advanced protocols coming with TAR 2.0.

    Get Full E-Book >>




  • Using TAR 2.0 to Expedite Multi-Language Review

    Download Using TAR Expedite Multi-Language Review

    How Insight Predict’s Unique Capabilities Cut Review by Two Thirds

    In a major shareholder class action alleging violations of federal securities laws, the defendant’s legal team was under a tight deadline to review a collection of mixed English and Spanish documents. By prioritizing documents using Insight Predict—Catalyst’s engine for technology assisted review—the team was able to cut the review by two-thirds, saving time and money.

    The case illustrates two key capabilities that distinguish TAR 2.0 platforms such as Insight Predict from earlier TAR tools. One is that judgmental seeds, selected by the trial team, were used to train the system, rather than the random seeds used by earlier tools. The other is that Insight Predict’s unique contextual diversity sampling helped discover critical information “hidden” in spreadsheet files.

    Read Full Case Study >>

  • Using TAR 2.0 to Streamline Document Review for Japanese Patent Litigation

    Download Using TAR 2.0 to Streamline Documents

    Continuous Active Review Cuts Cost by Over 85%

    Our client was a multinational Japanese company facing a large document production in an international patent dispute. The initial review collection exceeded 2 million documents. After a series of rolling uploads, which continued throughout the review, the population slated for review grew to 3.6 million. Facing millions in review costs, the client sought an alternative to linear review.

    Review time was short. The client’s goal was to finish the review in four weeks with a small team handling the project. The documents were primarily in Japanese, with some English in the mix, and many involved highly technical subject matter.


    Read Full Case Study | View Infographic| Watch the Video



About Catalyst

Catalyst designs, builds and hosts the world’s fastest and most powerful document repositories for large-scale discovery and regulatory compliance. We back our technology with a highly skilled Professional Services team and a global partner network to ensure the best e-discovery experience possible.
Catalyst Repository Systems

1860 Blake Street, 7th Floor
Denver, CO 80202

Phone: 303.824.0900 | Toll Free: 877.557.4273
Fax: 303.293.9073 |  Privacy PolicyPrivacy Shield


RT @acedsonline: [Exciting News!] @CatalystSecure releases FREE TAR e-book in their smart people series. Learn more:…

When your business is global, your #ediscovery will be too. Where in the world will your next legal matter arise?

ABA TECHSHOW Post-Mortem: Not Your Granddaddy’s Legal Tech Conference