BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Drupal iCal API//EN X-WR-CALNAME:Events items teaser X-WR-TIMEZONE:America/Toronto BEGIN:VTIMEZONE TZID:America/Toronto X-LIC-LOCATION:America/Toronto BEGIN:DAYLIGHT TZNAME:EDT TZOFFSETFROM:-0500 TZOFFSETTO:-0400 DTSTART:20190310T070000 END:DAYLIGHT BEGIN:STANDARD TZNAME:EST TZOFFSETFROM:-0400 TZOFFSETTO:-0500 DTSTART:20181104T060000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT UID:687488c76b382 DTSTART;TZID=America/Toronto:20190425T160000 SEQUENCE:0 TRANSP:TRANSPARENT DTEND;TZID=America/Toronto:20190425T160000 URL:/statistics-and-actuarial-science/events/david-spro tt-distinguished-lecture-damir-filipovic-epfl-and SUMMARY:David Sprott Distinguished Lecture by Damir Filipovic\, EPFL and Sw iss\nFinance Institute Senior Chair CLASS:PUBLIC DESCRIPTION:Summary \n\nA MACHINE LEARNING APPROACH TO PORTFOLIO RISK MANAG EMENT\n\n-------------------------\n\nRisk measurement\, valuation and hed ging form an integral task in\nportfolio risk management for insurance com panies and other financial\ninstitutions. Portfolio risk arises because t he values of constituent\nassets and liabilities change over time in resp onse to changes in the\nunderlying risk factors. The quantification of thi s risk requires\nmodeling the dynamic portfolio value process. This boils down to\ncompute conditional expectations of future cash flows over long time\nhorizons\, e.g.\, up to 40 years and beyond\, which is computation ally\nchallenging. \n\nThis lecture presents a framework for dynamic port folio risk\nmanagement in discrete time building on machine learning theo ry. We\nlearn the replicating martingale of the portfolio from a finite\n sample of its terminal cumulative cash flow. The learned replicating\nmar tingale is in closed form thanks to a suitable choice of the\nreproducing kernel Hilbert space. We develop an asymptotic theory and\nprove\nconverg ence and a central limit theorem. We also derive finite sample\nerror boun ds and concentration inequalities. As application we\ncompute the value a t risk and expected shortfall of the one-year loss\nof some stylized port folios.\n DTSTAMP:20250714T043415Z END:VEVENT END:VCALENDAR