Predictive coding in disclosure exercises

Author: Alice Morrissey

In Pyrrho Investments Ltd v MWB Property Ltd & Ors [2016] EWHC 256 (Ch), the English High Court has recently approved the use of predictive coding in the disclosure stage of High Court proceedings. In a nutshell, predictive coding is the practice of electronic document review carried out by sophisticated computer software rather than by human beings.  The software is trained to identify and classify relevant documents.

Amongst the factors in favour of approving the use of predictive coding in this case, Master Matthews noted that evidence suggests that predictive coding is “at least as accurate” as a manual review process and is already used in other jurisdictions.  Master Matthews also pointed out that a significant cost saving would be made in this case, where the costs of a manual review would be “unreasonable”.

Technology has in recent years transformed the way parties to legal proceedings manage the often overwhelming task of preparing and reviewing disclosure.  The use of e-disclosure platforms such as Relativity is now the norm in document heavy cases where the number of documents can run into millions.  The court’s approval of predictive coding is significant as, although the Civil Procedure Rules and its Practice Directions set out how electronic documents should be produced, they do not deal in detail with how the review process itself should be managed.  The court’s approval of predictive coding also highlights the judiciary’s growing acceptance of the need to embrace technological advances to improve the litigation process for both litigants and the court.

Alice Morrissey, Associate, Fladgate LLP (

View by date:

View by author:

Would you like to hear more?