Equivio is offering to make its early case assessment application Equivio>Relevance available to a limited number of participants in what they call the Equivio>Relevance Challenge – see the press release and sign-up page for details.
Most lawyers can understand the basic concepts of keyword search, if only because they do it every day with Google. Because one can generally find something out of the mass with a Google search, it is tempting to assume that throwing a list of keywords at disclosure / discovery data will reduce the volumes of data to be reviewed – and so, of course, it will. Many lawyers will understand, or at least be aware of, the idea that a keyword search is flawed as an approach to identifying relevant documents, not least because “relevance” turns on many factors beyond the incidence of a particular word or words in a document – correspondence between fraudulent conspirators will contain neither “fraud” nor “conspiracy”, to take a trite example.
Quite apart from anything else, Google is not designed to return everything and, even if it did, the weighting behind Google’s algorithms, immensely sophisticated though they are, has assumptions built into it which, whilst usually helpful for the context, does not amount to a defensible search strategy in a litigation context.
The difference with Equivio>Relevance is that it depends on input from skilled lawyers who review document samples and mark them as relevant or not relevant. Equivio>Relevance makes use of this input in an iterative and self-correcting way and produces a result which does not merely sort sheep from goats, as it were, but puts the most important sheep at the front of the queue so that correctly skilled (and correctly priced) lawyers can be applied to reviewing the documents. If the QA stage reveals flawed assumptions, the process can be re-run correcting them.
Conceptually, this is a lot to bite off, and the point of the Equivio>Relevance challenge is to give lawyers an opportunity to see for themselves what results from such an exercise.
Doubtless you can think of all sorts of reasons why this challenge is not for you. You probably do not have 1 million documents; that is not a prerequisite either for taking the Challenge or for using applications of this kind generally – the test is whether you can achieve the results which your clients need in less time and with less expense than by any other means, and Equivio are offering an opportunity for you to see that for yourself.
You may think that the UK court rules do not provide scope for the use of applications like this; if so, have a look at the Practice Direction to Part 31 CPR, paragraph 2A.5 of which reads as follows:
It may be reasonable to search some or all of the parties’ electronic storage systems. In some circumstances, it may be reasonable to search for electronic documents by means of keyword searches (agreed as far as possible between the parties) even where a full review of each and every document would be unreasonable. There may be other forms of electronic search that may be appropriate in particular circumstances.
Some are surprised to find even the reference to keywords, never mind the wide-ranging options which the last sentence gives – a deliberately-drafted expression which accepted (as has indeed been the case) that the technology of 2005 (when the PD was implemented) would quickly be overtaken by more sophisticated applications.
You might also, in this context, look at Senior Master Whitaker’s judgment in Goodale & Ors v The Ministry of Justice & Ors  EWHC B41 (QB) (05 November 2009) and specifically at paragraph 27 which reads as follows:
At the moment we are just staring into open space as to what the volume of the documents produced by a search is going to be. I suspect that in the long run this crude search will not throw up more than a few hundred thousand documents. If that is the case, then this is a prime candidate for the application of software that providers now have, which can de-duplicate that material and render it down to a more sensible size and search it by computer to produce a manageable corpus for human review – which is of course the most expensive part of the exercise. Indeed, when it comes to review, I am aware of software that will effectively score each document as to its likely relevance and which will enable a prioritisation of categories within the entire document set.
Master Whitaker may be ahead of his peers in his knowledge of such applications, but Lord Justice Jackson’s Report emphasised both the value of such applications and the need for judges, as well as lawyers, to understand what applications exist which can help with the problem of identifying the documents which matter.
Perhaps you think that there is something slightly suspect about a free offer, that fear of Greeks bearing gifts which I referred to in my recent article on a free trial. Equivio will doubtless provide references from the many users of Equivio>Relevance if you want comfort on that score.
That pretty well exhausts the list of possible excuses. One’s first experience of using applications like this is inevitably the hardest because one is grappling with new concepts at the same time as dealing with a large and presumably significant case. The opportunity to do so for free is hard to pass up.