Importance of the Technology Behind E-Discovery

The Importance of the Technology Behind e-Discovery Solutions


The sheer quantity and quality of data at the core of major investigations have reached new levels. It is no longer uncommon to have complex cases with tens and even hundreds of millions of disparate evidentiary files, including e-mail correspondence, significant financial and accounting records and other information. The need to organize, cluster, manage and timely exploit large volumes of information has become more pressing than ever.

Driven primarily by the advancements and adoption of technologies, particularly predictive analytics, the strategies employed by corporate legal departments for the utilization of e-Discovery software has and services is evolving. Looking back over the past two to five years, there was a trend not only to consolidate e-Discovery solution providers but also to move to providers who offer end-to-end services so to have an effective outcome indexing the correct data.

The driving force behind this trend was that disaggregation of the e-Discovery technology components, which resulted in both cost and process inefficiencies / false positives and created a risk with data handoffs and lack of transparency in end-to-end data validation. In response, some organizations consolidated providers, but still, the challenge was how pattern matching and regular expression technology behind e-Discovery led to extensive false positives.

Global challenge

Organizations face a multitude of electronic discovery requests that reach into all parts of the organization. They have the data but it is fragmented, duplicative and incomplete: finding it is ad hoc at best. On the other side, budgets are being cut and efficiencies must be found. In most of the cases, organizations need to cut costs even in the face of increasing mission demands.

With such strategic and tactical challenges across an organization, how can an organization achieve improved control of their data? Is the organization adequately equipped to maximize the knowledge stored in bit and pieces, here and there? Can the organization tackle the complexities and volume of both structured and unstructured data?

For containing the above challenges, enterprises should leverage advanced e-Discovery technologies with comprehensive fingerprinting capabilities with artificial intelligent proprietary algorithms; across both structured, semi-structured and structured data to  minimize false positives. They should emphasize on having an abstraction of e-Discovery modules within the software component parts – processing via fingerprinting detection capabilities hosting/production, and document review.

With this approach, e-Discovery software can promptly search terabytes of data, analyze the data population and potentially reduce the size of the review corpus regardless of file types on structured and unstructured data, constructing precise indexed results, which further can be parsed, culled, de-duped and so on.

It would further assist:

  • For fraud and other financial crimes investigations which are increasingly becoming more complex. Forensically gathering and exploiting immense quantities of sensitive information in a timely manner becomes key to investigative success.
  • In analyzing massive transactional data sets using business rules
  • Locating, scoping, acquiring, mining, testing, and verifying data in support of anomaly detection and fraud investigations
  • In reviewing large databases and financial systems
  • In providing investigative support of seized systems and data extraction and reports

Comments are closed.