| |
|
|
| |
In recent years,
there has been a great increase in the use of simulation techniques
in fields touched by actuaries. Financial firms and others who
advise or regulate them often need to estimate the value of
portfolios of assets and/or liabilities. At least one side of the
balance sheet is often too complicated to price analytically. In
such circumstances, regulatory regimes such as Solvency II favour
simulation-based methodologies to identify fair or
market-consistent values. These same organisations are also
typically obliged to develop risk measures quantifying the
(financial) risks to which such portfolios are exposed. For larger
organisations or ones with more complicated asset or liability
books, this can often introduce a need for nested simulations
involving so many calculations that runtimes can become important
constraints on how organisations can tackle such tasks.
These challenges are often in part subcontracted to specialist
teams or external suppliers. However, this does not absolve those
within the organisation guiding the relevant activities from
understanding what is going on, how robust are the relevant
calculations and whether it is possible to circumvent runtime and
other constraints in ways that may add value and reduce the costs
of carrying out such exercises.
During this web session we will explore some techniques that may
assist with these goals. We will pay particular attention to
techniques relevant to the calculation of risk measures and other
typically computationally more challenging problems actuaries can
face in such exercises. The techniques will range from the
conceptually simple, such as merely selecting fewer or a more
representative sample of simulations or parallelising computations
more efficiently, to the conceptually more complicated, such using
algorithmic differentiation, segmented Monte Carlo, artificial
intelligence techniques and novel computing technologies such as
quantum computing. The session will set these techniques within the
context of relevant regulatory guidance on how such exercises might
best be carried out.
Your early-bird registration fee is € 150.00 (net) / € 178.50
(incl. VAT, if applicable) for bookings by 23 December 2024. After
this date, the fee will be € 195.00 (net) / € 232.05 (incl. VAT, if
applicable). |
|
| |
|
|
|
