Dallas, USA, February 4, 2021 – Lineal, an Ai enabled legal technology services company has developed auto-classifying models in its review environment to pre-cull data sets and allow for incredible review gains. Lineal clients can immediately benefit from review efficiencies by implementing LTAi, the Lineal threading application built on NexLP’s advanced Ai algorithms. LTAi suppresses, on average, twice the amount of communication documents as any other industry threading application.
Lineal ECAi also includes an Ai Bot Detector that segregates out auto-generated (bot) messages, further reducing review communication populations by an average of 15%. Bot messages are ubiquitous in today’s communication data, showing-up as status updates, marketing reach-outs, reminder messages, etc. Lineal’s Bot Detector leverages communication analytics to accurately find messages from automated systems. It factors in the domain account (sender), the ratio between sends and replies, and the number of forwards of those messages, to determine the value of those accounts in the communication pool. All bot generated messages are then tagged, allowing for quick sampling review.
“ECA and threading are some of the areas where the industry seemed to need innovation. We strive for continuous improvement in all areas at Lineal, and ECAi is another example of how we deliver better outcomes because of this philosophy,” said Lineal CEO Kent Teague.
ECAi is available inside the Lineal Relativity Server instances, Lineal’s RelativityOne instances or Lineal’s Reveal environments.
About Lineal – Lineal Services is a legal data services organization leveraging AI and process-driven workflows to solve information governance, discovery, privacy, compliance, DSAR, conversion, and cyber issues for law firms and corporations. Headquartered in Dallas, and with offices throughout the North and South Americas, Europe, and Asia, Lineal has been delivering pioneering solutions since 2009.
Learn more at www.linealservices.com or follow us on Twitter and LinkedIn.