Events

ASTIN Webinar - Al in Actuarial Science
February 10, 2021
09:00 - 10:00 EST (click here to check your local time)

Deep learning techniques have begun to appear in the actuarial literature, and have produced promising results in several areas of actuarial practice. Building on a recent survey paper, this talk has as an aim to review the rationale for applying deep learning techniques within actuarial science and, in doing so, highlight the potential that these techniques hold for solving actuarial problems. Furthermore, as the application of these techniques begins to mature, new challenges are coming to light that we believe should be considered by the actuarial community, and we discuss some recently proposed solutions to these challenges. We then showcase some examples of how applying deep learning can increase the accuracy of actuarial modelling in classical and new fields and end with a case study on how the accuracy of mortality forecasting can be improved with deep learning techniques.

Ronald Richman

Ron is an Associate Director at QED Actuaries and Consultants, Africa’s largest independent actuarial consulting firm, where he is responsible for client work on life and general insurance clients and performing research into applications of machine learning and AI to actuarial and insurance topics. Before his current role, he led the Enterprise Risk Management and Actuarial teams for the AIG group within Africa. Ron tries to combine technical actuarial commercial expertise within the P&C and Life insurance sectors with a view of the possibilities enabled by modern machine and deep learning and has published several papers showing how these techniques can be applied for actuarial purposes. Ron is a Fellow of the Institute and Faculty of Actuaries (IFoA) and the Actuarial Society of South Africa (ASSA and a Masters of Philosophy in Actuarial Science, with distinction, from the University of Cape Town. Ron chairs the Actuarial Society of South Africa’s ERM committee and is a member of the Institute and Faculty’s Research and Thought Leadership Board.

IMPORTANT NOTES:
Once successfully registered, you will receive an automated response which will include a link to use to login on the day of the webinar.