The obligation to widely preserve potential evidence in legal disputes presents the costly challenge of reviewing large quantities of documents to find relevant information. The rapid expansion and manual review of ESI puts a strain on legal resources and increases the risk of missing significant facts in your case.
Technology Assisted Review (TAR) automates and organises your documents for review based on coding decisions made by your case team. By learning from human intervention, the software accelerates the review process minimising the time spent reviewing irrelevant documents.
Relativity supports two TAR technologies, Active Learning and Sample-based learning. Turn on Active Learning and simply start coding your documents. The system continuously learns from human decisions and updates the review queue so you receive the most likely relevant documents faster. Use Sample based learning to feed a coded set of documents to the system for Relativity to learn and categorise the remaining data set ranking the confidence of relevancy. Apply a QC workflow to improve the decisions the software made until you are satisfied with the results. Case deadlines, document volumes, data types all impact document review strategy and what TAR methods to apply.
London Legal consider best practice and advise on the right applications to use for an efficient and cost effective outcome. Our expertise, human review, and software knowledge are imperative to the success of TAR.
Technology Assisted Review amplifies the review of ESI, speeding up access to relevant information saving on eDiscovery costs and your internal resources.