12 Tips To Get The Most Out of Technology-Assisted Review ("TAR")

1. Decide which TAR approach best fits your needs and how you plan to deploy the solution: Do you want the seed set, predictive coding approach or the pattern-matching, rules-based approach? Seed set is good if you don't really know what you want, or you like to "decide on the fly." Rules-based is good if you know what you're looking for and can explain it (similar to how you would train contract attorneys for a large-scale review).


2. Similarly, do you want TAR as a service or do you want to install a product? Products are typically lower-cost, but less featured or customizable to your specific needs. Services typically cost more, but usually include expert analysis and consulting as part of the package. One consideration in product vs. service is how frequently you encounter a need for TAR and how similar each instance is to the next. Higher frequencies would lead you towards a product, but low similarities across needs would lead you towards services. Remember to include both hard costs (typically dollars outlaid) and soft costs (such as training time and expenses, storage needs, platform support, etc.) in your analysis.


3. Be realistic about how much you will rely on the coding performed by tool or process and what level of QC you will require. Will you eventually have "eyes on" every document or will you only put "eyes on" subsets of the documents based on relevance or issue criteria? Understanding this early will help you to make the right decisions on pricing, implementation and staffing.


4. Get comfortable with pricing metrics conversions. Some solutions are sold per document or file, some per GB and some per hour. Here's how to translate between those metrics. Assume: ~ 6,000 docs/files per GB (post processing), and ~ 50 docs/files reviewed per person per hour. Now you can compare pricing for different solutions!


5. Be explicit about your needs. Do you want a simple yes/no answer for privilege or do you want to know which types of privilege are being invoked? Ex: attorney-client vs. work product. Same for relevance. Is it enough to know simply that a document is relevant or do you need to know why it is relevant (and/or to what degree)?


6. Map out your workflow and strategy. You (or your client) will need to defend your document production approach. For maximum defensibility, make sure your process is repeatable and transparent. Be wary of TAR solutions that do not disclose why or how propagated decisions are made. Be similarly cautious of solutions that yield different results when different people are "manning" them. Furthermore, make sure that the provider will back you up by providing tangible proof to support the defensibility of the process.


7. Understand that TAR is an iterative process. The more guidance and feedback you provide, the stronger the results will be. Do not expect the first round to be perfect. You and the systems will both get better over time. As a rough rule of thumb, expect 4-5 iterations.


8. Think about Exception Handling. Even the best TAR solutions will encounter "problematic" documents from time to time. How will you handle hand-written documents, custom application files or documents written in foreign languages? A good TAR solution should be able to easily identify the docs/files it cannot handle and remove them from the automated processing queue. In other words, don't pay twice for documents that will ultimately need manual processing.


9. Make good use of Issue Codes. Most sophisticated TAR solutions can handle multiple Issue Codes, providing very helpful tagging and organizational information for Hot or Responsive documents. A consultative TAR solution provider can help you maximize your Issue Codes protocol so that it complements and enhances the production.


10. Be aware of potential privacy concerns. Many document collections have sensitive or personally identifying information (PII) in their contents that cannot be openly shared. Sophisticated TAR techniques identify, cull and/or automatically redact this information prior to production. TAR approaches can save many hours of manual effort to cleanse data for production.


11. Choose your solution carefully. Expect that your needs will change over time, both in general and across a single matter. Ideally, the solution provider has full, unfettered access to the TAR engines, so that they can be custom-tailored to your (or your client's) exact circumstances. Be wary of "one size fits all" solutions.


12. TAR Beyond Document Productions. TAR has uses far beyond review for responsive and privilege. Consider utilizing the techniques when you (or your client) are on the receiving end of a large volume of data. TAR processes can be extremely cost-effective at organizing, cataloging and indentifying trends and data threads in incoming material.

Valora Technologies CEO, Sandra Serkes, Responds to Craig Ball’s LTN Article on “Next Level” Technology Assisted Review

Original article: Imagining the Evidence

I am pleased to inform both Mr. Ball and the world that the “next level” of TAR, meaning the use of whole documents and populations, rather than selected seed sets, is already here and doing fine.  Rules-Based approaches to TAR are not constrained by the need to create and perfect the selection of a seed set.  Instead, they apply their algorithms and iterations across the entire population, at once, each time.  There is no need for any exemplar document, as the exemplar is the rule itself – thus any document can be evaluated for its “exemplary-ness” and to what degree, where and when.

Furthermore, Mr. Ball discusses the thorny issue of self-interested collection and seed set tagging.  He suggests the opposing party should be the one to set the seed set tags into motion.  This is a step in the right direction.  But, the best approach would be to have both producing and opposing working together to determine relevance – an option easily afforded by a Rules-Based approach.  Rather than having any one party have to sit down and hand-craft a seed set, both sides can agree on the RULES of responsiveness, rather than on whether this document or that one is the better exemplar.  With agreed-upon rules in place, documents are easily assessed not just for yes/no relevance, but also to what degree.

Finally, the notion of “imagining” the documents is very much alive and well in the field of Data Visualization.  We often use this technique in a descriptive way (here’s what your data shows), but it can also very much be used in a proscriptive way (is there anything that looks like this?  How close?).  This concept is very much connected to the current practice of iterating for performance optimization (aka: trading off precision and recall).  TAR systems that utilize the notion of DocType or Attribute templates already have the concept of a “generic” or “iconic” version, essentially an exemplar.  It is trivial to create more templates and use them in a hierarchical manner to test how much a potential document matches the generic exemplars, by relevance priority.

Valora Technologies CEO, Sandra Serkes, Invited to Speak to ILTA South Pacific Region About Technology Assisted Review

ILTA Program to Cover "Exploring Predictive Coding and Technology Assisted Review: Valora Technologies' Approach"

July 25, 2012, 6:00pm EST

During her presentation, Ms. Serkes will layout the Technology-Assisted review (TAR) landscape and Valora Technologies' overall approach.  With Document Review the most costly phase of ediscovery, there are considerable savings to be achieved when it's possible to automate some or most of that review process in a reliable and defensible manner.  This theory is the motivation behind the hype about predictive coding and TAR. Unlike most of the solutions on offer in this market space, Valora Technologies' approach is Rule-Based and transparent.  Come learn about the developing TAR landscape and one provider's unique vision for this space.

Remote & physical presentation sign-up now open.

3 Drawbacks To Predictive Coding

Valora’s Response to LTN article: Take Two: Reactions to 'Da Silva Moore' Predictive Coding Order

What is missing there, and elsewhere, is a discussion of the specific weaknesses of the overall Predictive Coding technique.  Here are just three drawbacks of the technique: 

1. PC tagging algorithms are not transparent.  No one really knows why the PC engine "chose" the documents it did.  Typically, the “choosing” algorithm is hidden and not disclosed.  All we know is that somehow the document recognized is a lot like another tagged.  
2. PC has no checks or balances on the skill set, education, consistency or motivations of the seed set coder(s).  The entire Predictive Coding approach assumes that the seed set coder(s) know what they are doing, and that they are correct, consistent and honest.  Would you defend that position, particularly given that the “human being as gold standard" concept has been roundly deflated (see Blair & Maron, Grossman, TREC, etc.)?
3. Typically, seed set creation and audit sampling for PC use a random sampling technique, the weakest of all types. 

Other sampling techniques (stratified, cluster, panel, etc.) are aware of document attributes and utilize intelligent groupings to create a much stronger, more representative sample for seed set coding and auditing purposes.

Since at present, all Predictive Coding solutions are products, which means they have limited functionality and flexibility for specific case matters, perhaps we should be thinking about the broader picture of Technology-Assisted Review (TAR) as a service – customizable, measurable and transparent.

Valora's position on Judge Peck's Commentary in (Da Silva v. Moore) Transcript

The transcript, articles and subsequent brouhaha are overblown. It is obvious that the parties are not particularly debating the efficacy of predictive coding, but rather the proper way to implement it, particularly when there are changes to the population volume or to the relevancy specifications. What is interesting to all of us is this:

Why is there so much wrangling over the size of the seed set and the need to re-seed it with changes?

How should such TAR systems and workflow handle changes? What are the differences between changes to document volume (count) and changes to review specifications?

Why has this ignited the blogosphere, to the point of blatant fact distortion?

There is considerable wrangling over the seed set because of 2 reasons: control and comfort. Judge Peck alludes to the second notion with his distinctions between a statistical sample and a "comfort sample." (His words.) The client service folks in the audience are laughing at this notion as they know full well the mistrust their clients have in "the numbers," while the statisticians present are utterly confounded. Surely, the statistical sample is in fact the most comfortable sample, anything else would be downright uncomfortable!

And, so we get to the second issue here: control. By registering vague, ill-described discomfort with the numbers, the attorneys regain some control by playing on fear. What don't we see? What didn't we get? As Judge Peck points out, it's not about the miniscule "misses," but rather the overall "sure-fires" and the ability to build a case around those.

One of the big problems in this matter is the conflating of two separate types of changes: changes in population size (adding documents) and changes in relevancy scope. These changes are completely independent of one another and should be managed separately. The size change affects the random sampling and so it should be regenerated each time new docs are added. The scope change affects the seed set coding and so it should be regenerated as well to reflect current, up-to-date specifications. In fact, the seed set coding should never be out of step with current specs, or it is obsolete. A far better TAR workflow design than random sampling to generate a seed set and fixed tagging of it is to assume change is part of the litigation and build in mechanisms to manage it. For starters, the seed set should be stratified per the attributes of the then-current document population, rather than random. It should be regenerated every time docs are added or removed. Next, a transparent, easy to edit ruleset should be used to track spec changes and show those over time as documents change their tags. Finally, TAR systems should be priced so that there is no disincentive to make such changes easily.

And finally, why all the hoopla? Because we all know that deep down this is where it is all going. In some ways we are rooting for Recommind (even if we would consider ourselves a competitor) because TAR is the better solution: lower cost, faster and more accurate. Now, if we could be smart about sampling, seed sets and inevitable changes to spec and volume, we'd really have something to shout about.