As the saying goes, “there’s more than one way to skin a cat”; TAR is also called Machine Assisted Review (MAR), Computer Assisted Review (CAR), Predictive Coding, Concept Search, or Meaning-based computing: all of which are marketing terms without any specific scientific meaning
Though still an emerging practice, automatic classification of content is gaining momentum (finally) due to recent court decisions regarding the use of predictive coding: “… in 2012, a federal district court held that ‘predictive coding’ using software trained by lawyers to identify and classify relevant documents could be substituted for lawyers manually searching for and reviewing every potentially relevant document
When you consider purchasing a system with advanced functionality that depends on content analytics (such as automatic record classification, automatic legal review, predictive coding, etc
So what is the answer? Predictive coding. Jason believes that predictive coding is very well suited to solving the “keep everything approach” and our governance issues
From the perspective of a Records Manager working down in the weeds to actually do RM in a federal govt. environment (as opposed to those who make RM policies/procedures and invent ERM technology “solutions”), it was simply not believable that software algorithms and/or “predictive coding” technology could be relied on to accomplish this complex task with any acceptable degree of accuracy/success
Predictive Coding - What if you were searching a collection of documents, looking for a single maintenance record that confirmed reasonable due diligence vs negligence in a failed mechanical system?
Example – Big Data, Predictive Coding, Cloud THREATS – What changes in technology are threatening your ability to manage information?
Document classification and machine learning technology in eDiscovery are gaining attention under new names such as technology-assisted review (TAR), machine-assisted review (MAR), computer-assisted review (CAR) and predictive coding
All information, including non-record, has some type of value, even if only transitory, so every scenario should be accounted when creating policies, predictive coding and auto classification/categorization rules
One of the most promising technological developments in recent years is the concept of predictive coding (or auto-classification) of large document sets