BLP wins first contested application to use Predictive Coding technology in disclosure

Article

Posted by , , on

Summary: BLP has won the first contested application to use Predictive Coding as part of a substantial document review exercise. BLP is one of only a few firms with in-house data processing, hosting and document review capabilities, and virtually unique in having in-house Predictive Coding technology. This order is a significant win for the client and the team, and an excellent demonstration of the value of this technology.

In February, Master Matthews provided the first reported English High Court decision approving the use of predictive coding technology for electronic disclosure, at the request of both parties, in Pyrrho Investments Ltd v MWB Property Ltd & Ors [2016] EWHC 256 (Ch).  This marked a long anticipated judicial affirmation for use of this disruptive technology in the UK legal market (by contrast with the US, where the technology has been in active use for some time).

However, as Master Matthews noted, “whether it would be right for approval to be given in other cases will, of course, depend upon the particular circumstances obtaining in them”; and one of the key considerations in the Pyrrho case was the consensus of the parties regarding its proportionality, efficacy, and suitability.  On 17 May 2016 the High Court ordered, for the first time, the use of predictive coding in the face of disagreement between the parties as to its suitability.

Key facts of the case

The case concerns an unfair prejudice petition in which the petitioner seeks a buy-out of his minority shareholding.  The respondents strongly contest the allegations, and the valuation suggested by the petitioner.  The parties nevertheless reached agreement on most case management directions in advance of the first Case Management Conference.  The most substantial point of dispute was over the most appropriate and proportionate approach to disclosure by the respondent who, it was accepted, held the significant majority of the potentially relevant documents.

The petitioner’s solicitors wished to adopt a “traditional” approach to document review, whereby the inboxes of an agreed a list of custodians would be filtered using an agreed list of search terms, and the responsive documents would be reviewed in a linear fashion by a paralegal resource.  BLP, representing the respondent, asserted that the costs of this approach would be excessive, and that superior results could be achieved at a more proportionate cost using predictive coding technology.

What is predictive coding?

Predictive Coding is machine learning technology driven by human tuition.  A senior lawyer reviews a small "seed set" of documents, which is then analysed by the technology and used to generate a further sample for review.  Through a process of iterative refinement, the algorithm can reach a level of review accuracy that can be applied across the entire dataset, identifying relevant documents in a manner that is far more efficient and scalable than a traditional document review.  A series of sample reviews, privilege sweeps, and other human interventions can then be used to verify the results and finalise the documents prior to exchange.

Cost of predictive coding

It was estimated that a traditional linear review would cost more than two and a half times the cost of predictive coding.  A significant factor in being able to achieve this level of cost savings was the fact that BLP could run the predictive coding work in-house, rather than needing to pay an external technology provider to provide daily rate access, support, hosting fees, and so forth.  Despite all this, the petitioner resisted the use of predictive coding, and so the approach to disclosure came to be considered at the first Case Management Conference.

The court’s decision

Counsel for the respondent referred the court to the relevant passages of Pyrrho Investments v MWB and the ten factors set out by Master Matthews in favour of using predictive coding.  Of those, one was not applicable (factor 10: “The parties have agreed on the use of the software, and also how to use it, subject only to the approval of the Court”) and one was neutral (factor 4: “There is nothing in the CPR or Practice Directions to prohibit the use of such software”).  All of the other factors weighing in favour of using predictive coding in Pyrrho also applied in the instant case.

On this basis, the court ordered that predictive coding be used by the respondents’ solicitors in this case, marking the first such order made without the consent of all parties.  It is also a clear demonstration that predictive coding technology is not only suited to handling claims with exceptionally large datasets (such as the 3 million documents in Pyrrho, after de-duplication), but can also be critical to achieving proportionality in smaller claims involving more typical datasets (approximately 500,000 documents in this case).

BLP’s attitude to legal technology

BLP is a strong advocate for the use of emerging technologies to improve the quality and efficiency of legal work, and has already won multiple awards for its pioneering technologies such its real estate data extraction robot.  We are one of only a few firms with an in-house data processing, hosting and document review capability, and almost unique in having an in-house Predictive Coding resource.

This latest court order is a significant win for the client and the BLP team, and an excellent demonstration of the opportunity provided by this technology; predictive coding not only reduces the cost of e-disclosure, but also operates at a higher level of accuracy than a traditional human review.  It also opens up new opportunities such as early case assessment, since it enables lawyers to quickly identify the most highly relevant documents at a much earlier stage than through a traditional review.

If you would like to know more about predictive coding, contact nick.pryor@blplaw.com.  If you would like to hear more about how we can assist you in resolving disputes more generally, contact oliver.glynn-jones@blplaw.com.

This site uses cookies to help us improve our services and your browsing experience. For further information about cookies, including about how to change your browser settings to no longer accept cookies, please view our privacy policy.