This paper elaborates on scenario aggregation for regulatory purposes. The existing approach proposed with the Swiss Solvency Test (SST) is presented and discussed. We then propose a more general and coherent framework for scenario aggregation based on divergence from the reference probability measure subject to scenario constraints. The continuity of standard risk measures with respect to changes in the reference probability measure is discussed. This new scenario aggregation approach is the illustrated with examples. 1 Background The last decades have seen strong developments in the statistical measurement of risk. The quantitative methods used by banks and insurances for risk management serve many purposes such as capital allocation or reporting to regulators. The latter have required regulated institutions to implement and document internal models that, once approved, should be used to report their amount of capital which is bearing the risk and to show that they would remain solvent in case of extreme scenarios. Although the risk modeling methodology of an insurance company’s internal model is reported and subject to approval, model risk remains inherent and should therefore be challenged. The risk of inappropriate modeling can be raised at many levels. One could question a specic
[1]
Christine M. Anderson-Cook,et al.
Book review: quantitative risk management: concepts, techniques and tools, revised edition, by A.F. McNeil, R. Frey and P. Embrechts. Princeton University Press, 2015, ISBN 978-0-691-16627-8, xix + 700 pp.
,
2017,
Extremes.
[2]
P. Embrechts,et al.
Model Uncertainty and VaR Aggregation
,
2013
.
[3]
Solomon Kullback,et al.
Information Theory and Statistics
,
1970,
The Mathematical Gazette.
[4]
Attilio Meucci,et al.
Fully Flexible Views: Theory and Practice
,
2008,
1012.2848.
[5]
Terry J. Lyons,et al.
Stochastic finance. an introduction in discrete time
,
2004
.
[6]
Multivariate stress scenarios and solvency
,
2012
.
[7]
J. Kemperman,et al.
On the Optimum Rate of Transmitting Information
,
1969
.
[8]
Attilio Meucci,et al.
The Black-Litterman Approach: Original Model and Extensions
,
2008
.
[9]
I. Csiszár,et al.
Stress Tests: From Arts to Science
,
2010
.
[10]
S. Fang,et al.
Entropy Optimization and Mathematical Programming
,
1997
.
[11]
Stephen P. Boyd,et al.
Convex Optimization
,
2004,
Algorithms and Theory of Computation Handbook.