IT-Discovery

Brains

IT-Discovery as a technology is the practical application of a science developed at Universities for data mining large amounts of text, using topics derived from social network analysis in the service of search.

The Death of Linear Review

In the world of linear review, where all documents are “created equal” there is necessarily an enormous amount of wasted time. Given a large warehouse of unmarked boxes one has no choice but to read every document in any order.

At the heart of IT-Discovery is a machine learning technology that allows us to create a system of filing cabinets that makes order of that enormous warehouse of jumbled documents, automatically. In the real world, not all documents are created equal with respect to the focus of your investigation, or more broadly, “context” is crucial for understanding “text”. So who says something can matter as much as what is said, and when something gets said is of often seminal. That’s why topics are at the core of our application. Our product files irrelevant jokes with other irrelevant jokes, and critical documents with other critical documents, before you have even begun. Such global “clustering” is unique to IT-Discovery.

Corpus Reduction: Machines Learning from Humans

So called “supervised” learning technology – machines using training sets of data as samples – is also incorporated into IT-Discovery. From a small sample set, the system can generate, via a feature we call Corpus Reduction, the likely set of non-responsive documents. Senior reviewers can choose to hide non-responsive documents from results to quickly focus their attention on documents most likely to be responsive. At any time corrections can be made and Corpus Reduction run again to improve results. The system only gets smarter the more it’s used.

Search Triangulation

All search technology uses at most two axes with which to form a query. IT-Discovery offers three. Via topic modeling, you have an idea of what is discussed. Through the choice of custodians or author/recipients, a precise statement of who discussed that topic. And through traditional keyword search, a demand that certain words be used in some specified way. Such triangulation is unique to IT-Discovery.