Regardless of the method used to preserve data from a social networking site, it is important to remember these seven key points.
Technology Assisted Review (TAR), computer assisted review, predictive coding, clustering, categorization, themes, analytics, support vector-based TAR, concept-based TAR, email threading, near duplicate detection, sampling, machine learning – these are just a few of the terms that come up when talking about TAR. Here is a TAR cheat sheet to help keep the terms straight!
Is there a difference between “Predictive Coding” and “Technology Assisted Review”?
When does it make sense to use PC/TAR?
What are the risks in using PC/TAR?
Is it defensible?
Read the answers to these and over 10 more Frequently Asked Questions here.
As the law evolves to address new media distribution channels, courts will have to predict how people on both sides of the content will inevitably abuse the system.
Judge Maas decided that sanctions were not warranted despite the fact that plaintiffs willfully deleted ESI belonging to relevant custodians.
Corporations allocate significant time and money for protecting their digital intellectual property. 7 Tips for better Law Firm Security
The primary benefit of TAR is to prioritize documents within a corpus by likelihood of relevance as early as possible in the eDiscovery lifecycle.
LIVE from LegalTech NY 2013 is a compilation of blogs and insights from D4′s Engineers that attended the conference. They recapped the sessions that they thought were outstanding or just plain interesting and put them all in one place for you to enjoy.
As a service provider we perform a lot of intake on new electronic discovery projects. We see the difference between legal teams who have thoroughly interviewed custodians and IT staff, and those who either have not, or if they have, they didn’t ask many questions about ESI in any quantified or documented way.
In this whitepaper you will learn 6 expert tips to remember for your next eDiscovery client interview.
By Tom Groom, Vice President, Discovery Engineering, D4
Keyword Search, Concept Based Search and Support Vector Machines are all three valid approaches for document classification but there are key differences that should be considered before deciding which and—perhaps more importantly, when—to employ these approaches in the eDiscovery workflow. The intent of this white paper is to highlight the differences in the features, functions and benefits of these three approaches and identify potential application areas where they best work in the eDiscovery lifecycle