Visualizing Data in a Predictive Coding Project – Part Three

By Ralph Losey

This is part three of my presentation of an idea for visualization of data in a predictive coding project. Please read part one and part two first. This concluding blog in the visualization series also serves as a stand alone lesson on the basics of math, sampling, probability, prevalence, recall and precision. It will summarize some of my current thoughts on quality control and quality assurances in large scale document reviews. Bottom line, there is far more to quality control than doing the math , but still, sampling and metric analysis are helpful. So too is creative […]

Read the complete article at: Visualizing Data in a Predictive Coding Project – Part Three

Location. Location. Location.

By Craig Ball

I’m peripatetic. My stuff lives in Austin; but, I’m in a different city every few days. Lately looking for a new place for my stuff to await my return, I’m reminded of the first three rules of real estate investing: 1. Location; 2. Location and 3. Location. Location has long been crucial in trial, too: “So, you claim you were at home alone on the night of November 25, 2014 when this heinous crime was committed!  Is that what you expect this jury to believe?”   If you can pinpoint people’s locations at particular times, you can solve crimes. […]

Read the original article at: Location. Location. Location.

Your ROI Is Coming Out of My Pocket

By Michael Simon

Our modern lives are filled with black boxes, things that we understand in terms of the inputs they require (click the mouse, turn the wheel, insert slice of bread) and the outputs we receive (your computer beeps, your car turns, you get toast!).  Yet between the input and the output there are a whole bunch of things happening that we can’t see, can’t explain, and – most importantly – don’t actually need to explain to accomplish our desired task.  As long as the inputs are understandable and the outputs are what we expect, what lies in between can be completely opaque.  I don’t need to know how my toaster works, as long as I get my toast.

So why is the fact that machine learning (a/k/a “predictive coding”) is a black box such a problem?  Is it because human review of documents (i.e., an eyes-on-all-docs full review) is somehow more transparent?  Of course not.  We have study after study of the greater accuracy and effectiveness of review assisted by machine learning (when used properly).

Read the complete article at: Your ROI Is Coming Out of my Pocket

2014 eDiscovery Trends: Survey Results

By Michele Lange

With about six weeks remaining in the year, let the “2014 reflections” bombardment begin! You know what I am talking about — the close of the calendar year prompts oodles of nostalgic news stories recalling the biggest events of the year. Okay, I will admit it…about this time last year, I willingly clicked on Google’s Top Ten Trending Stories of 2013 and BuzzFeed’s The 27 Movies We Loved in 2013. There is just something about this time of year that makes us want to ponder the past.

So, wholeheartedly jumping in to the “year in review” spirit, Kroll Ontrack surveyed over 550 law firm and corporate ediscovery professionals to gauge the biggest trends and impacts in ediscovery in 2014. This was a great year for the world of ediscovery, and now is the perfect time to share some of the interesting 2014 trends with all of you. To see the full set of ediscovery trends, please download the “2014 Ediscovery Trends: Industry Survey Results” guide.

Read the complete article at: 2014 eDiscovery Trends: Survey Results

Visualizing Data in a Predictive Coding Project – Part Two

By Ralph Losey

This is part two of my presentation of an idea for visualization of data in a predictive coding project.Please read part one first.

As most of you already know, the ranking of all documents according to their probable relevance, or other criteria, is the purpose of predictive coding. The ranking allows accurate predictions to me made as to how the documents should be coded. In part one I shared the idea by providing a series of images of a typical document ranking process. I only included a few brief verbal descriptions. This week I will spell it out and further develop the idea. Next week I hope to end on a high note with random sampling and math.

Vertical and Horizontal Axis of the Images

The visualizations here presented all represent a collection of documents. It is supposed to be pointillistimage, with one point for each document. At the beginning of a document review project, before any predictive coding training has been applied to the collection, the documents are all unranked. They are relatively unknown. This is shown by the fuzzy round cloud of unknown data.

Read the complete article at: Visualizing Data in a Predictive Coding Project – Part Two

TAR in the Courts: A Compendium of Case Law about Technology Assisted Review

By Bob Ambrogi

Magistrate Judge Andrew Peck It is less than three years since the first court decision approving the use of technology assisted review in e-discovery. “Counsel no longer have to worry about being the ‘first’ or ‘guinea pig’ for judicial acceptance of computer-assisted review,” U.S. Magistrate Judge Andrew J. Peck declared in his groundbreaking opinion in Da Silva Moore v. Publicis Groupe . Judge Peck did not open a floodgate of judicial decisions on TAR. To date, there have been fewer than 20 such decisions and not one from an appellate court. However, what he did do — just as [...]

Read the complete article at: TAR in the Courts: A Compendium of Case Law about Technology Assisted Review

Turkeys, Thanksgiving and Predictive Coding (Cartoon and Clip)

The Cartoon and Clip of the Week for November 14, 2014

Daily we read, see and hear more and more about the opportunities, challenges and concerns associated with predictive coding. This week’s cartoon and clip highlights a visual depiction of two knowledge workers taking a random sampling approach to predictive coding (cartoon) and some considerations for thinking about the challenges associated with textual analytics-based technology-assisted review platforms. (clip).

---

Text and Non-Text Files in Information Governance and eDiscovery

When you are evaluating information governance and electronic discovery solutions do you ask your vendor/service provider the basic questions of:

1) Does your system or process identify both textual and non-textual ESI files?

2) How does your system or process index and classify non-textual ESI files? (Example: Image only PDFs.)

3) How does your system or process identify text within non-textual ESI files? (Example: Graphics with words published to an image only PDF.)

If your vendor/service provider cannot adequately answer these three simple questions, then you may want to consider the potential risk and exposure associated with not fully considering non-textual ESI in your information governance and eDiscovery efforts.  Additionally, if your vendor is relying on a non-automated process for classifying non-textual files, then you may not be using the most efficient approach for your information governance or eDiscovery efforts.

Click here to find a running listing of some of the latest postings on the topic of Technology-Assisted Review.