Time to Work Smarter, Not Harder
The ediscovery landscape is proving to be more treacherous given the rise of data proliferation and the increase in sanctions for mismanaging ESI. As the courts grow increasingly intolerant of discovery failures, litigants are faced with two choices: work harder by investing more resources to ensure thorough review, or work smarter by leveraging fewer resources with cutting-edge technology to achieve superior results. Dynamic companies know the latter is always the best option, and for them, the next generation of ediscovery technology has arrived.
Intelligent Review Technology
Intelligent Review Technology (IRT) combines the best of both worlds by delivering the discerning analytics of a human review team in a platform capable of increased processing speed, consistency and accuracy. Although IRT encompasses many different technologies that can work independently or conjunctively to varying degrees, workflow automation, supervised learning and statistical quality control are the cornerstone features of an effective IRT system that together allow review to be conducted faster, more efficiently and accurately than even the best human review teams equipped with current discovery technology. Key Features of IRT
IRT begins at the foundation of review by offering a solution to workflow management; an arduous, tedious process with relatively simple substance and highly complex logistical qualities that make it ripe for automation. Rather than relying on a finite number of human review administrators with limited capacity, workflow provides greater processing bandwidth resulting in increased work capacity, a remarkably high attention to detail and, importantly, the flexibility to handle varying workloads. Managing the review process on a workflow platform also allows the system to simultaneously track all stages of the project and produce accurate, real-time metrics, progress reports and statistical analysis. In the July 2010 case of Multiven v. Cisco Systems, Inc.,1 the Northern District of California was forced to intervene in order to expedite the discovery and review process. Amidst a slow-moving document review, numerous discovery disputes and a looming deadline, the parties were ordered to split the costs of employing an ediscovery vendor and the court appointed a special master to oversee the remainder of the discovery process. Multiven highlights the formidable challenges of modern discovery – managing costs, meeting deadlines and conducting efficient reviews – that can be resolved through supplementing discovery projects with IRT. Indeed, the scenario in this case represents a discovery dilemma that would benefit from the speed, efficiency and progress tracking that could be gained from a heavier reliance on technology.
Another important IRT feature is supervised learning, which replaces the need to rely on a search expert to build search queries or predictive models. Instead, a supervised learning algorithm creates a classifier, which is a predictive model capable of sorting through documents, determining the responsiveness and then assigning each to the correct class with a remarkably high degree of accuracy. This highly advanced technology achieves this by iteratively analyzing samples of documents that have been classified and categorized by a human reviewer in order to “learn” the distinguishing characteristics of what constitutes responsive versus nonresponsive, privileged versus non-privileged, etc. The resulting expression of this difference is the classifier, which is then applied to non-reviewed documents. A particularly remarkable trait of some classifiers is the capability to assign a degree of confidence to their classification decisions. The result is a rating system that can be used to prioritize documents on a graduated scale of responsiveness rather than a more tenuous one-or-the-other categorization. The substantial benefits of this technology include more effective search queries, greater consistency and a reduced need for human resources.
Statistical quality control is also a critical part of any review process, whether conducted traditionally or using supervised learning. Through use of IRT, statistical sampling helps guide the review process by accurately identifying the most responsive documents, allowing the human reviewers to be appropriately tasked to those documents in which their skills are most suited. Perhaps more important than guiding attorneys during the review process, sampling can also help signal when the review process should end by estimating the proportion and probability of responsive documents remaining. In Mt. Hawley Ins. Co. v. Felman Prod. Inc.,2 the Southern District of West Virginia made clear that sampling is a critical quality control process that should be conducted throughout the review. The court found the plaintiff failed to perform this task, which weighed heavily on its decision to waive privilege on an inadvertently produced “smoking gun” email aptly referred to by the court as the “proverbial tip of the iceberg,”considering it is almost certain to sink the plaintiff’s claim. Although complicated and challenging, proper statistical sampling likely could have prevented this costly error from occurring. IRT makes the complicated sampling process simpler and more accurate by testing data samples to improve the accuracy and efficiency of calculating statistical data, ultimately resulting in a more defensible and reliable review.
Advanced search technologies work well and remain optimal for many projects, but as ediscovery scope and complexity continue to climb, the disparity between cost and effectiveness will only increase. IRT closes the gap and delivers value through greater cost predictability, strengthened defensibility, increased speed and less reliance on human resources. IRT is a broad term that represents an expansive range of advanced ediscovery tools, but workflow, supervised learning and statistical quality control are key features that must be insisted upon in any IRT system. As discovery costs remain the most expensive portion of litigation expenses, corporations and law firms are well advised to explore the numerous and substantial benefits IRT has to offer.
12010 WL 2813618 (N.D.Cal. July 9, 2010).
22010 WL 1990555 (S.D.W.Va. May 18, 2010.