Aisenstadt Chair

[ Français ]

Alexander J. McNeil (University of York)
Stay: September 18 - October 6, 2017

McNeil Alexander McNeil has been Professor of Actuarial Science at the University of York since September 2016. Educated at Imperial College London and Cambridge University, he was formerly Assistant Professor in the Department of Mathematics at ETH Zürich and Maxwell Professor of Mathematics in the Department of Actuarial Mathematics and Statistics at Heriot-Watt University, Edinburgh, where he founded and led the Scottish Financial Risk Academy (SFRA) between 2010 and 2016. Professor McNeil’s research interests lie in the development of quantitative methodology for financial risk management and include models for market, credit and insurance risks, financial time series analysis, models for extreme risks and correlated risks, and enterprise-wide models for solvency and capital adequacy. Professor McNeil has published numerous papers in leading statistics, actuarial, econometrics and financial mathematics journals. He is a regular speaker at international risk management conferences. He is an Honorary Fellow of the (British) Institute and Faculty of Actuaries and a Corresponding Member of the Swiss Association of Actuaries.




First talk

Vendredi 22 septembre / Friday, September 22

15h30 / 3:30 pm

Conférence s'adressant à un large auditoire scientifique [ Diaporama / Slideshow ] [ Video ]
Lecture suitable for a general scientific audience

Centre de recherches mathématiques
Pavillon André-Aisenstadt
Université de Montréal
Salle / Room 6214

Quantitative Risk Management under Basel III

Diapos /Slides

To some extent quantitative risk models in banking have been in retreat since the 2007-9 financial crisis, in contrast to the situation in the European insurance industry where Solvency II has taken a highly quantitative approach. We look at the reasons for this retreat and survey the current regime for capital charges with particular emphasis on the new rules for market risk in the trading book. A bank which wants to apply internal models in the calculation of capital charges is now subject to a much more rigorous model validation process. We explain how this process works and use this to frame the current academic debates around the elicitability and “backtestability” of risk measures. An interesting academic literature has sprung up around these issues and advanced the statistical theory of forecasting. However, it is not yet whether these advances will find their way into the practice of risk management and the regulation of the financial industry. We will give an accessible overview of the mathematics and statistics involved in these issues and offer thoughts about the future of quantitative risk management (QRM) and the increasing importance of model validation in the banking industry.

Une réception suivra la conférence au salon Maurice L'Abbé, Pavillon André-Aisenstadt (salle 6245).

A reception will follow the lecture at the Salon Maurice-L'Abbé, Pavillon André-Aisenstadt (room 6245).

Second talk

Vendredi 29 septembre / Friday, September 29
14h30 / 2:30 pm
McGill University Burnside Hall
805 rue Sherbrooke Ouest
Salle / Room 1205

Spectral Backtests of Forecast Distributions with Application to Risk Management

In this talk we study a class of backtests for forecast distributions in which the test statistic is a spectral transformation that weights exceedance events by a function of the modelled probability level. The choice of the kernel function makes explicit the user’s priorities for model performance. The class of spectral backtests includes tests of unconditional coverage and tests of conditional coverage. We show how the class embeds a wide variety of backtests in the existing literature, and propose novel variants as well. We assess the size and power of the backtests in realistic sample sizes, and in particular demonstrate the tradeoff between power and specificity in validating quantile forecasts.

Third talk

Vendredi 6 octobre / Friday, October 6
13h30 / 1:30 pm
HEC Montréal
3000, chemin de la Côte-Sainte-Catherine
Salle Banque Scotia (section bleue),
1er étage / Room Banque Scotia (Blue section),
1st floor

Scenario Sets, Risk Measures and Stress Testing

We examine the relationship between multivariate scenarios sets and risk measures. Our interest is motivated by the use of scenario sets in the stress testing of banks and insurance companies whose portfolio values and solvency are dependent on changes in underlying financial risk factors. Although regulators suggest that financial institutions should consider extreme but plausible scenarios, there is no clear guidance on exactly how this should be done. We explain the connection between sets based on the notion of half-space depth (HD) and the Value-at-Risk risk measure. We then introduce general depth concepts related to coherent risk measures and show how these lead to scenario sets based on, for example, the expectile or the expected shortfall risk measure. We consider the construction of multivariate scenario sets and the implementation of stress tests in practice. In the case of elliptically distributed risk factors, all of the depth-based scenario sets coincide with regions encompassed by the contours of the density function. Our particular interest lies in skewed and/or heavy-tailed multivariate risk factor distributions, where the equivalence of depth contours and density contours does not hold in general; we present a number of example to illustrate the issues that can arise.