BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//hacksw/handcal//NONSGML v1.0//EN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20260610T212825Z
DESCRIPTION:Click for Latest Location Information: http://edw2023digital.da
 taversity.net/sessionPop.cfm?confid=155&proposalid=14174\nFINRA receives ov
 er 60,000 triggering events annually. The events range from investor compla
 ints, regulatory tips, arbitration claims, and member firm disclosures. Dur
 ing very high market volatility periods, FINRA receives spike volumes of tr
 iggering events and all of these events have to be triaged within tight SLA
 s.\n\nThis presentation will focus on how FINRA experimented with multiple 
 machine learning models to predict the severity and allegations that are pr
 esent in the incoming triggering events to FINRA. Furthermore, the presenta
 tion will focus on a serverless architecture to build a near real-time solu
 tion that helps FINRA investigators to focus on high-priority events, there
 by safeguarding market integrity and protecting investors from bad actors.&
 nbsp;\n
DTSTART:20230328T124000
SUMMARY:From Data to Insights – How FINRA Uses Machine Learning
DTEND:20230328T132959
LOCATION: See Description
END:VEVENT
END:VCALENDAR