eDJ Contributor: Karl Schieneman
He has trained dozens of judges on advanced analytic review tools including Judge Peck (Da Silva Moore case), Judge Grimm, Judge Scheindlin, Judge Francis, Judge Maas, and many judges in the W.D. of Pennsylvania. He is also known nationally as the host of www.ESIBytes.com, the country’s largest collection of free E-Discovery podcasts; the creator of www.DocReviewMD.com, a blog site focused on improving document review process with predictive coding tools, and the creator of ReviewRight®, the country’s first web based test for document review attorneys. Recently he assisted the 7th Circuit E-Discovery Pilot program by drafting an overview piece describing predictive coding approaches and served in their CLE presentation hosted by judiciary in the 7th Circuit.
Over the course of his 18 year legal career, Karl has worked with E-Discovery technology at JurInnov, pioneered the use of contract attorneys nationally as the founder of Pittsburgh based Legal Network, which was acquired by Special Counsel, and practiced law at Pittsburgh based Marcus & Shapira. He received an MBA from Carnegie Mellon University and graduated on Law Review and Cum Laude from the University of Pittsburgh School of Law. Some of his past honors include receiving an Ernst & Young Entrepreneur of the Year Award in 2004, a Vestige Award for Most Innovative Use of ESI in 2008 and has been involved with Inc 5000 Award Winning Companies in 7 years with three different companies.
Posts by Karl Schieneman
hide story details [-]
- April 30th
-
DUKE Conference on TAR – The Experts Convene
On April 19th, 60 invited delegates convened on Washington, DC to discuss with the Federal Rules Committee to discuss Technology Assisted Review. The object of the meeting was to have the delegates give their perspectives on whether the Rules currently being readied for public comment should incorporate changes that take into account the unique needs of TAR. My overall conclusion is that the Duke Conference was an outstanding event and it went along way to show that attorneys need more transparency when using TAR or it becomes very hard to effectively cooperate.
posted at 9:00am on Apr 30th
- April 15th
-
ESIBytes Podcast with Judge Nora Barry Fischer Explains Predictive Coding Boot Camps
Last week Barry Murphy and I recorded an ESIBytes podcast on the rationale behind the eDiscoveryJournal and Review Less predictive coding boot camp national “tour” beginning in Washington, DC on April 17th, with a special guest Judge Nora Barry Fischer a Federal District Court Judge from the W.D. of Pennsylvania who is one of the Judges assisting with the judicial roundtable portion of the predictive coding boot camp. Judge Fischer kicked off the podcast by reiterating the need for more e-discovery education by sharing some recent observations from the e-Discovery Special Master program from the W.D. of PA. This showed that eDiscovery is occurring more frequently in cases and highlighted the need for lawyer education in the field. This problem is especially acute when we talk about newer technologies such as predictive coding which requires some understanding of statistics to be able to understand the [...]
posted at 10:56am on Apr 15th
- February 11th
-
Global Aerospace Case Highlights Need For Predictive Coding Education
At least a dozen friends have inquired about my health after the big push of Global Aerospace news came out last week, since there were no blog posts by me. As a participant in the case, I figured it was more important to let others weigh in on the significance of this decision as a precedent that predictive coding can be defended in a court. The verdict came despite fierce opposition by a very well respected, (and deservedly so I might add), Amlaw 20 law firm which ultimately settled the case after the judge issued his order allowing the use of predictive coding. It is also worth mentioning that Judge Chamberlin was an unknown quantity going in, unlike Judge Peck in Da Silva Moore. As many of you know, Judge Peck had been embracing and educating lawyers and judges on [...]
posted at 9:00am on Feb 11th
- December 18th
-
HOLIDAY COLLECTIONS AND HOW RUDOLPH CAN SAVE eDISCOVERY
On September 9, 2011 I presented to a blue ribbon panel of in-house lawyers, outside counsel and judges at the Committee Meeting on Preservation and Sanctions in the Western District of Pennsylvania who were in agreement with my thesis that we over preserve, collect and process ESI in proportion to what is eventually used. My views on this topic have been evolving over time and I outlined this for the panel with a contrast of the Rand Study, Where the Money Goes with the Microsoft Letter dated August 29, 2011. The Rand Study reported that, for the seven corporate participants, collection costs were estimated to be only $.08 of every dollar spent on eDiscovery, with the bulk of the expenses going to processing, and review. The studies’ authors and I tended to diminish the importance of these more minor collection [...]
posted at 4:23pm on Dec 18th
- November 27th
-
PREDICTIVE CODING METRICS ARE FOR WEENIES PART IV
I have been writing a series of posts about the “ever-elusive” metrics that many eDiscovery professionals seem to be waiting for when it comes to driving mainstream adoption of TAR. Does the elusive challenge of finding and providing these TAR metrics mean we are doomed not to be able to use TAR? No, it means clearly that lawyers, who have that rare blend of statistical training and court room experience, have a huge advantage in arguing in discovery disputes. The fact is there are boatloads of metrics that a smart litigator can use to defend their process. One analogous observation is the joke people have about statisticians. That two statisticians can argue forever that they are right on opposite sides of many issues by using statistics. We are going to have these arguments given the fact that the richness of [...]
posted at 9:00am on Nov 27th
- November 13th
-
PREDICTIVE CODING METRICS ARE FOR WEENIES PART III
My last two posts have focused on the predictive coding metrics that so many eDiscovery professionals are waiting for with bated breath. What is the real problem here? It’s not that we don’t have standards which are reasonableness or proportionality, or that we don’t have metrics which are present almost everywhere you look when considering these tools. The problem is that lawyers don’t think in large enough numbers to understand the meaning of the basic metrics they have in front of them. Most of the basic metrics can be validated by simple sampling principles to not only make an argument that their approach is reasonable, but also to know when to disagree with an opponent in the heat of battle. It is much easier for an opponent of TAR to give a blanket statement about not wanting to miss any [...]
posted at 9:00am on Nov 13th
- November 5th
-
PREDICTIVE CODING METRICS ARE FOR WEENIES – Part II
My recent piece, “Predictive Coding Metrics are for Weenies – Part I,” looked at how those who want metrics that will suddenly “validate” predictive coding are going to get left behind waiting for that validation. To examine the fence sitters’ concerns more closely, I agree it would be nice to know in advance if the number of random sample documents your TAR system uses is enough to train it adequately. If the system is looking at 5,000 documents as a training set, is that enough? Or, should it be something smaller, such as 2,000 documents? Or whether the final recall rate of responsive documents found should be an estimated 70, 80, or 90 percent of the total responsive documents in the collection (recall is the measure used to determine what percentage of responsive documents were found out of the total [...]
posted at 6:12pm on Nov 5th
- October 31st
-
Judicial Activism with Predictive Coding – All In The Name of “Just”, “Speedy” and “Inexpensive” Discovery
I had a spirited discussion on Friday with a litigator about whether it was appropriate for Honorable J. Travis Laster from the Delaware Chancery Court to push the parties to use predictive coding when apparently neither of the parties sought to use predictive coding in EORHB, Inc., et al v. HOA Holdings, LLC, C.A. No. 7409-VCL (Del. Ch. Oct. 15, 2012). I decided to take some time to think about this outcome since I have been very public in my support of using predictive coding to reduce many of the ills of the litigation system, e.g. lengthy discovery disputes, excessive costs and uneven quality of ESI productions. Yet I am also on record supporting the outcome of Kleen Products where the plaintiffs failed in forcing the defendants to use predictive coding because they had what appeared to be an uphill battle to impose their discovery will on their adversary. I also generally believe parties should be able to chart their own course for how to proceed with discovery.
posted at 9:00am on Oct 31st
- October 29th
-
PREDICTIVE CODING METRICS ARE FOR WEENIES – Part I
I recently read an assessment from a morning networking meeting held in Chicago about Technology Assisted Review (TAR), that those in attendance believed we needed more metrics around predictive coding tools to help end users grasp how to effectively use them. This assessment struck me as bizarre because metrics are the very essence of TAR. Common metrics encountered with TAR are the “richness” of a collection,( e.g. how many documents are relevant in a collection being reviewed versus the total population of documents in the collection), and “recall rates” or how many documents the TAR system is finding when compared to the bench mark rate of expert human reviewers on the same sample of documents. In addition to this, the decision of when to stop or to continue training a TAR system, which is likely based on some combination of [...]
posted at 9:00am on Oct 29th
- October 17th
-
The “E’s” of Predictive Coding – Part Two
Before I get a string of emails from my fellow experts and friends in the field, I must add that creating new processes in law is never easy because of the barriers pointed out earlier in this post. Also, the additional skills of understanding technology, statistics and law does make each of us experts, even if we are throwing out competing preferred routes to complete a review and confusing the marketplace. Just like your GPS, the customers end up with three suggested routes to choose from and they all get you from A to Z crossing different types of terrain. But, since lawyers are trained to avoid risk and would rather use “precedent” as opposed to coming up with new solutions, there is a risk of following blindly a single route as gospel without doing some homework about the different routes and their applicability for the specific matter at hand.
posted at 8:21pm on Oct 17th
