Data Analytics

Our data analytics tools are grounded in best of breed technologies that have the ability to identify patterns between words, terms and concepts that do not require any prerequisite human input (such as word lists, dictionaries or other linguistic structures or ontologies). Our tools are then able rapidly classify and put the results into sortable lists, as well as identify other responsive documents that more traditional searching techniques may have overlooked. However, the challenge of data analytics is bringing a legal team’s understanding of the technology to the level of the technology itself in order to create massive speed, efficiency and cost-savings across eDiscovery engagements. Our expert team of project management staff regularly advises our clients on the pros and cons associated with each data analytics technology, and will patiently work with legal teams to implement the most quick, efficient and cost-effective workflow for document review engagements.

Below is a sampling of some of the data analytics services that our expert team offers:

  • Clustering: Allows for legal teams to immediately identify conceptually similar document via “clusters” that they can review, sort, filter and dig deeper into.
  • Keyword Expansion: Utilizes a particular iteration of a search term, and returns all words with similar meanings, such as “gas”, “oil” or “petroleum”.
  • Concept Searching: Accepts for the searching of sentences or multiple paragraphs of text to see how and where the same ideas and concepts intersect with other similar ideas and concepts across your matter.
  • Email Threading: Identifies redundant email content, such as earlier responses on email chains that were captured in subsequent email chains or duplicative email chains, which your team can then set aside in order to decrease the total amount of content which will require document review, thereby reducing your total legal spend.
  • Near-Duplicate Detection: A technology that groups documents with similar text content at customizable textual similarity thresholds that legal teams can then create searches and quality control workflows to search across near-duplicate groups to enhance accuracy and consistency in their document review process.