If you are interested in learning more about predictive coding, I would highly recommend the white paper from TechTarget entitled, “Using Predictive Coding To Your E-Discovery Advantage.” The white paper contains three articles and below is a brief summary of each one.
The first article is “Predictive Coding: It’s Not Just For E-Discovery Anymore” by Marilyn Bier, CEO of ARMA International. The article starts out discussing information governance and it has this great bulletin board quote on information governance.
Solid information governance is always the best approach to maximizing records and information as business assets and minimizing business risks… Poor information governance will likely result in a data management disaster whereby records are lost, retained too long, disposed of improperly, made vulnerable to breaches, and subjected to other undesirable ends that weigh heavily on an organization’s bottom line and its reputation.
The author then proceeded to discuss what predictive coding is and how it has been used in e-discovery. She next shared the view point of Leigh Isaacs from Orrick, Herrington & Sutcliffe LLP and Doug Smith of Wiley Rein LLP and how predictive coding can be used for more than just e-discovery, but also information governance. Isaacs added this to the predictive coding and information governance discussion.
predictive coding increases information identification accuracy by pairing subject matter experts with predictive coding technologies. This pairing provides a solid foundation for defensible disposition and prevents content from being retained too long. The technologies can also help a company cull its data to identify valuable intellectual property; locate vital records and contracts that may have been misfiled; identify sensitive information for the purposes of protection and compliance; and much more.
Smith went on to contribute the following:
predictive coding offers an alternative to the manual, subjective process of coding and quality review, which is laden with inefficiencies and inaccuracies…Predictive coding can help remediate the problem by creating a classification schema that identifies and categorizes the information that’s housed in unstructured or less-formal systems,
The next article is “The Value of the Human Eye in Predictive Coding” by Christine Parizo. This article defines predictive coding for those unfamiliar with the process and gives the legal precedence of e-discovery acceptance gaining acceptance in different court cases. One of the big takeaways for me is that predictive coding is not an out of the box solution, but it is a system that needs to be trained.
The key to consistency is making sure the right people are training the system, said David Sun, president of Washington, D.C.-based consultancy SunBlock Systems Inc. “It’s reliable in the sense that, whatever you tell it to do, it will do many times over.”
For example, a lawyer may tell a predictive coding system to only look for documents containing keywords, while a programmer may expand the keyword searches to include misspellings.
The last article is entitled, “Data Discovery Tools Done Right” by Ben Cole. The author presents a high level overview of different e-discovery tools and strategies that can aid in information governance.
By definition, e-discovery tools identify where an organization stores data, as well as what the data is used for, how it’s distributed and by whom. If used correctly, e-discovery tools can be used to pinpoint this sensitive data and help develop processes to protect it.
Cole looks at network analysis and visibility and data loss prevention tools to discover data for the purpose of identifying and classifying it. By doing this an organization can increase security and protection by applying controls and policies to restrict access. Other advantages include streamlining information and procedures as well as better archiving and identifying large amounts of data to delete before applying security controls.