Article (Scientific journals)
A Markov-switching Generalized additive model for compound Poisson processes, with applications to operational losses models
Hambuckers, julien; Kneib, Thomas; Langrock, Roland et al.
2018In Quantitative Finance, 18 (10), p. 1679-1698
Peer Reviewed verified by ORBi
 

Files


Full Text
HMM_GAM for GPD regression.pdf
Author preprint (670.06 kB)
Supplementary material available upon demand
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
GAMLSS; Hidden Markov model; operational losses; generalized Pareto distribution; compound Poisson process; distributional regression
Abstract :
[en] This paper is concerned with modeling the behavior of random sums over time. Such models are particularly useful to describe the dynamics of operational losses, and to correctly estimate tail-related risk indicators. However, time-varying dependence structures make it a difficult task. To tackle these issues, we formulate a new Markov-switching generalized additive compound process combining Poisson and generalized Pareto distributions. This flexible model takes into account two important features: on the one hand, we allow all parameters of the compound loss distribution to depend on economic covariates in a flexible way. On the other hand, we allow this dependence to vary over time, via a hidden state process. A simulation study indicates that, even in the case of a short time series, this model is easily and well estimated with a standard maximum likelihood procedure. Relying on this approach, we analyze a novel dataset of 819 losses resulting from frauds at the Italian bank UniCredit. We show that our model improves the estimation of the total loss distribution over time, compared to standard alternatives. In particular, this model provides estimations of the 99.9% quantile that are never exceeded by the historical total losses, a feature particularly desirable for banking regulators.
Research center :
Chair of Statistics and Econometrics, Faculty of Economics
Disciplines :
Quantitative methods in economics & management
Author, co-author :
Hambuckers, julien ;  Université de Liège - ULiège > HEC Liège : UER > Statistique appliquée à la gestion et à l'économie
Kneib, Thomas
Langrock, Roland
Silbersdorff, Alexander
Language :
English
Title :
A Markov-switching Generalized additive model for compound Poisson processes, with applications to operational losses models
Publication date :
2018
Journal title :
Quantitative Finance
ISSN :
1469-7688
eISSN :
1469-7696
Publisher :
Routledge
Volume :
18
Issue :
10
Pages :
1679-1698
Peer reviewed :
Peer Reviewed verified by ORBi
Name of the research project :
RTG 1644 Scaling problem in Statistics
Funders :
DFG - Deutsche Forschungsgemeinschaft [DE]
Available on ORBi :
since 14 December 2017

Statistics


Number of views
130 (12 by ULiège)
Number of downloads
214 (5 by ULiège)

Scopus citations®
 
9
Scopus citations®
without self-citations
6
OpenCitations
 
9

Bibliography


Similar publications



Contact ORBi