Predictive Coding is not a Magic Wand

Predictive coding is a process by which attorneys review a small sample of a large volume of documents, according to their specifications. Their review pattern is then applied to the larger document set using a “content clustering” or “find-similar” calculation.

This allows a large number of documents to be reviewed without attorneys having to spend thousands of hours looking at each page. Predictive coding is used as a supplement to traditional e-discovery filtering methods, such as keyword searching.

The variables in this process include the selection of documents for the sample set, the user response to the sample set and the computer algorithms that are applied. In a project where predictive coding is used, it’s true that processing costs will increase, but there will be substantial savings in the review phase – assuming that the project was well-planned and managed from the outset, and that the process and technology were used appropriately.

At its core, predictive coding is about workflow. The thought behind predictive coding – that technology can help reduce the cost of e-discovery – is solid, but figuring out what technology to apply at what point in the workflow is not always easy. Having other attorneys or consultants who are seasoned in e-discovery analyze your workflow or case (particularly for large projects) can save much time and money.

Ultimately, predictive coding is not just about using technology, but about using it well and using it at the right time.