Computing semiparametric bounds on the expected payments of insurance instruments via column generation

Robert Howley, Robert Storer, J. C. Vera, Luis F. Zuluaga

Research output: Contribution to journalArticleScientificpeer-review

Abstract

It has been recently shown that numerical semiparametric bounds on the expected payoff of financial or actuarial instruments can be computed using semidefinite programming. However, this approach has practical limitations. Here we use column generation, a classical optimization technique, to address these limitations. From column generation, it follows that practical univariate
semiparametric bounds can be found by solving a series of linear programs. In addition to moment information, the column generation approach allows the inclusion of extra information about the random variable, for instance, unimodality and continuity, as well as the construction of corresponding worst/best-case distributions in a simple way.
Original languageEnglish
Pages (from-to) 34-50
JournalVariance
Volume10
Issue number1
Publication statusPublished - 2016

Keywords

  • Distributionally robust optimization
  • Moment problem
  • Option Pricing
  • Insurance instruments

Cite this

Howley, Robert ; Storer, Robert ; Vera, J. C. ; Zuluaga, Luis F. / Computing semiparametric bounds on the expected payments of insurance instruments via column generation. In: Variance. 2016 ; Vol. 10, No. 1. pp. 34-50.
@article{0b4c04f918904f1a9728ed2f627363a6,
title = "Computing semiparametric bounds on the expected payments of insurance instruments via column generation",
abstract = "It has been recently shown that numerical semiparametric bounds on the expected payoff of financial or actuarial instruments can be computed using semidefinite programming. However, this approach has practical limitations. Here we use column generation, a classical optimization technique, to address these limitations. From column generation, it follows that practical univariatesemiparametric bounds can be found by solving a series of linear programs. In addition to moment information, the column generation approach allows the inclusion of extra information about the random variable, for instance, unimodality and continuity, as well as the construction of corresponding worst/best-case distributions in a simple way.",
keywords = "Distributionally robust optimization, Moment problem, Option Pricing, Insurance instruments",
author = "Robert Howley and Robert Storer and Vera, {J. C.} and Zuluaga, {Luis F.}",
year = "2016",
language = "English",
volume = "10",
pages = "34--50",
journal = "Variance",
issn = "1940-6444",
number = "1",

}

Computing semiparametric bounds on the expected payments of insurance instruments via column generation. / Howley, Robert; Storer, Robert; Vera, J. C.; Zuluaga, Luis F.

In: Variance, Vol. 10, No. 1, 2016, p. 34-50.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Computing semiparametric bounds on the expected payments of insurance instruments via column generation

AU - Howley, Robert

AU - Storer, Robert

AU - Vera, J. C.

AU - Zuluaga, Luis F.

PY - 2016

Y1 - 2016

N2 - It has been recently shown that numerical semiparametric bounds on the expected payoff of financial or actuarial instruments can be computed using semidefinite programming. However, this approach has practical limitations. Here we use column generation, a classical optimization technique, to address these limitations. From column generation, it follows that practical univariatesemiparametric bounds can be found by solving a series of linear programs. In addition to moment information, the column generation approach allows the inclusion of extra information about the random variable, for instance, unimodality and continuity, as well as the construction of corresponding worst/best-case distributions in a simple way.

AB - It has been recently shown that numerical semiparametric bounds on the expected payoff of financial or actuarial instruments can be computed using semidefinite programming. However, this approach has practical limitations. Here we use column generation, a classical optimization technique, to address these limitations. From column generation, it follows that practical univariatesemiparametric bounds can be found by solving a series of linear programs. In addition to moment information, the column generation approach allows the inclusion of extra information about the random variable, for instance, unimodality and continuity, as well as the construction of corresponding worst/best-case distributions in a simple way.

KW - Distributionally robust optimization

KW - Moment problem

KW - Option Pricing

KW - Insurance instruments

M3 - Article

VL - 10

SP - 34

EP - 50

JO - Variance

JF - Variance

SN - 1940-6444

IS - 1

ER -