The supreme body of the pension fund (board of trustees) is responsible for the overall management of the pension fund. The non-transferable and inalienable duties of the supreme body include the following tasks among others: the setting of the financing system and comprehensibly designing, monitoring, and controlling the asset management to improve the returns and benefits for the members of the pension fund. Since being a member of the board of trustees is not a full-time job, the scope of duties is enormous: meeting the aforementioned legal requirements requires a lot of time and expertise. Pension fund accredited actuaries, investment consultants, auditors as well as pension fund management teams should fully support the board of trustees to make proper decisions.

The reliable forecast of liabilities is very important for the determination of the pension funds' financing system and its control (with risk budgeting). Since many liability parameters depend on the development of yield curves and inflation, it is worthwhile to prepare the analysis of their historical data, visualize them and additionally forecast them reliably.

The aim of this web session is to show how useful the yield curve and inflation forecasting are with the deep learning approach, the visualization of the results and the liability forecast based on them. These approaches are implemented using Python (Anaconda/Jupiter) and R-Project. This type of analysis helps the board of trustees to make their decisions and to better understand the forecast results (compared to affine models). In addition, we will show that such approaches are useful for forecasting international accounting results (IFRS, US GAAP, IPSAS) and for preparing asset allocation to be the strong third contributor.

Organised by the EAA – European Actuarial Academy GmbH.

The web session is suitable for pension fund actuaries and actuarial professionals, pension fund managers and IT developers for pension fund administration tools who are directly or indirectly involved in providing actuarial and investment advice to pension funds and collective foundations with occupational pension benefits. In addition, these topics may also be useful for pension fund boards of trustees and auditors for international accounting.

Technical Requirements
Please check with your IT department if your firewall and computer settings support web session participation (the programme Zoom is used for the web session). Please also make sure that you are joining the web session with a stable internet connection. 

The aim of this web session is to provide insights into the approach to forecasting liabilities, inflation, and yield curves for risk budgeting analysis - including the reliable deep learning approach.

The language of the web session will be English.

Dr Ljudmila Bertschi
Ljudmila is a qualified member of the Swiss Association of Actuaries (SAV/SAA) and an accredited pension fund 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 (SKPE).

Dr Mauro Triulzi
Mauro is a qualified member of the Swiss Association of Actuaries (SAV) and holds a Dr. math. ETHZ. He has been working as a developer of actuarial tools for about 20 years and implemented nested stochastic modelling of pension fund liabilities including mortality rates for ALM studies. He is currently developing various actuarial tools for local and international accounting and pension fund management. Together with Ljudmila, he has prepared presentations for international conferences.