EAA Web Session: Machine Learning Finance for Pension Funds with Examples
Announcement from the EAA organiser:
In general, Machine Learning (ML) is the study of algorithms that improve through experience. These algorithms or models can make systematic, repeatable, validated decisions based on historical data. ML has come a long way in recent years, which is reflected in the methods available for time series forecasting (they are also important for assessing parameters for different kinds of liability provisions). Therefore, this type of analysis can help actuaries and members of pension fund boards of trustees to accurately assess different kinds of pension fund parameters for assets and liabilities and to prepare any kind of forecasts. Visualizing the evolution of pension fund parameters and forecasting them will help the board of trustees explain how to adjust them in the actuarial provision or what to expect in their future evolution. For this workshop, several examples for analyzing and providing such assumptions will be prepared and explained. Many useful visualization techniques will be presented with practical examples (via Python).
The annual financial statement of a pension fund shows all very important parameters of the liabilities as well as all types of reserves. Machine Learning Finance helps to verify all levels of reserves and to prepare the annual financial statement presentation for the members of the Board of Trustees - this helps them to make their final decisions.
Click here. (Note: timing via that link is in CEST [Central European Summer Time].)
Dr Ljudmila Bertschi
Ljudmila is a qualified member of the Swiss actuarial association (SAV/SAA) and an accredited pension actuary of the Swiss chamber of pension fund experts (SKPE). She has a PhD in phys. math. from the MSU and has worked in pension fund consulting for about 20 years in different Swiss and international consulting firms and insurance companies. She conducted a research study for the Federal Office of Social Security (2015), prepared many publications and presentations for international conferences as well as made training presentations for Swiss chamber of pension fund experts (liability forecasting with Markov chains incl.).
Dr Mauro Triulzi
Mauro is a qualified member of the Swiss actuarial association (SAV) and has a Dr. math. ETHZ. He has worked for about 20 years as a developer of actuarial tools and implemented the nested stochastic modelling for pension fund liabilities including mortality rates for ALM studies. Currently he develops different actuarial tools for local and international accounting valuations as well as pension fund administration services. He prepared presentations for international conferences together with Ljudmila.