Excess based allocation of risk capital

Research output: Contribution to journalArticleScientificpeer-review

Abstract

In this paper we propose a new rule to allocate risk capital to portfolios or divisions within a firm. Specifically, we determine the capital allocation that minimizes the excesses of sets of portfolios in a lexicographical sense. The excess of a set of portfolios is defined as the expected loss of that set of portfolios in excess of the amount of risk capital allocated to them. The underlying idea is that large excesses are undesirable, and therefore the goal is to determine the allocation for which the largest excess is as small as possible. We show that this allocation rule yields a unique allocation, and that it satisfies some desirable properties. We also show that the allocation can be determined by solving a series of linear programming problems.
Original languageEnglish
Pages (from-to)26-42
JournalInsurance: Mathematics & Economics
Volume50
Issue number1
DOIs
Publication statusPublished - 2012

Fingerprint

Excess
Linear programming
Division
Risk capital
Minimise
Series
Capital allocation
Expected loss
Allocation rules

Cite this

@article{a3fa8e9d52944dd98757eb8c36515e47,
title = "Excess based allocation of risk capital",
abstract = "In this paper we propose a new rule to allocate risk capital to portfolios or divisions within a firm. Specifically, we determine the capital allocation that minimizes the excesses of sets of portfolios in a lexicographical sense. The excess of a set of portfolios is defined as the expected loss of that set of portfolios in excess of the amount of risk capital allocated to them. The underlying idea is that large excesses are undesirable, and therefore the goal is to determine the allocation for which the largest excess is as small as possible. We show that this allocation rule yields a unique allocation, and that it satisfies some desirable properties. We also show that the allocation can be determined by solving a series of linear programming problems.",
author = "{van Gulick}, G. and {De Waegenaere}, A.M.B. and H.W. Norde",
note = "Appeared earlier as CentER Discussion Paper 2010-123",
year = "2012",
doi = "10.1016/j.insmatheco.2011.09.003",
language = "English",
volume = "50",
pages = "26--42",
journal = "Insurance: Mathematics & Economics",
issn = "0167-6687",
publisher = "Elsevier Science BV",
number = "1",

}

Excess based allocation of risk capital. / van Gulick, G.; De Waegenaere, A.M.B.; Norde, H.W.

In: Insurance: Mathematics & Economics, Vol. 50, No. 1, 2012, p. 26-42.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Excess based allocation of risk capital

AU - van Gulick, G.

AU - De Waegenaere, A.M.B.

AU - Norde, H.W.

N1 - Appeared earlier as CentER Discussion Paper 2010-123

PY - 2012

Y1 - 2012

N2 - In this paper we propose a new rule to allocate risk capital to portfolios or divisions within a firm. Specifically, we determine the capital allocation that minimizes the excesses of sets of portfolios in a lexicographical sense. The excess of a set of portfolios is defined as the expected loss of that set of portfolios in excess of the amount of risk capital allocated to them. The underlying idea is that large excesses are undesirable, and therefore the goal is to determine the allocation for which the largest excess is as small as possible. We show that this allocation rule yields a unique allocation, and that it satisfies some desirable properties. We also show that the allocation can be determined by solving a series of linear programming problems.

AB - In this paper we propose a new rule to allocate risk capital to portfolios or divisions within a firm. Specifically, we determine the capital allocation that minimizes the excesses of sets of portfolios in a lexicographical sense. The excess of a set of portfolios is defined as the expected loss of that set of portfolios in excess of the amount of risk capital allocated to them. The underlying idea is that large excesses are undesirable, and therefore the goal is to determine the allocation for which the largest excess is as small as possible. We show that this allocation rule yields a unique allocation, and that it satisfies some desirable properties. We also show that the allocation can be determined by solving a series of linear programming problems.

U2 - 10.1016/j.insmatheco.2011.09.003

DO - 10.1016/j.insmatheco.2011.09.003

M3 - Article

VL - 50

SP - 26

EP - 42

JO - Insurance: Mathematics & Economics

JF - Insurance: Mathematics & Economics

SN - 0167-6687

IS - 1

ER -