ARCHIVED CONTENT
You are viewing ARCHIVED CONTENT released online between 1 April 2010 and 24 August 2018 or content that has been selectively archived and is no longer active. Content in this archive is NOT UPDATED, and links may not function.By Sandra Serkes
Predictive Coding (really, data analytics) is a means for harnessing (or suppressing) the potential information locked in large data sets – aka Big Data. Whether the data set is a collection of a litigant’s corporate emails, a call log of customer complaints at a retail establishment, or an entire state’s tax forms, the starting point is the same: a big, ol’ collection of stuff. And once there is a document population, there is information contained within. The debate begins with whether that hidden information is helpful (an asset), or harmful (a liability), or perhaps both. It progresses with whether or not it is worth the cost, time and effort to find out; and concludes with what to do about it once the status is known (or could reasonably become so). This last point is essentially Information Governance, and the path from technology-optimized litigation document review to full-on information management and control is a short one. The techniques used in predictive analytics for document review are essentially the same as those used in much broader application of the same capabilities. This chapter explores the use of data analytics for understanding, diagnosing, organizing, managing, mining, forecasting and reporting on all manner of document data well beyond litigation and eDiscovery purposes.
Read the complete paper at: (DESI VI Workshop)
Source: ICAIL 2015