TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Calibration of GARCH models using concurrent accelerated random search

Tutkimustuotosvertaisarvioitu

Standard

Calibration of GARCH models using concurrent accelerated random search. / Müller, Juliane; Kanniainen, Juho; Piche, Robert.

julkaisussa: Applied Mathematics and Computation, Vuosikerta 221, 2013, s. 522-534.

Tutkimustuotosvertaisarvioitu

Harvard

APA

Vancouver

Author

Müller, Juliane ; Kanniainen, Juho ; Piche, Robert. / Calibration of GARCH models using concurrent accelerated random search. Julkaisussa: Applied Mathematics and Computation. 2013 ; Vuosikerta 221. Sivut 522-534.

Bibtex - Lataa

@article{d96e5f075e934b89a65a98b2584bb42c,
title = "Calibration of GARCH models using concurrent accelerated random search",
abstract = "This paper investigates a global optimization algorithm for the calibration of stochastic volatility models. Two GARCH models are considered, namely the Leverage and the Heston-Nandi model. Empirical information on option prices is used to minimize a loss function that reflects the option pricing error. It is shown that commonly used gradient based optimization procedures may not lead to a good solution and often converge to a local optimum. A concurrent approach where several optimizers (“particles”) execute an accelerated random search (ARS) procedure has been introduced to thoroughly explore the whole parameter domain. The number of particles influences the solution quality and computation time, leading to a trade-off between these two factors. In order to speed up the computation, distributed computing and variance reduction techniques are employed. Tests show that the concurrent ARS approach clearly outperforms the standard gradient based method.",
author = "Juliane M{\"u}ller and Juho Kanniainen and Robert Piche",
note = "Contribution: organisation=tta,FACT1=0.5<br/>Contribution: organisation=ase,FACT2=0.5<br/>Portfolio EDEND: 2013-07-29<br/>Publisher name: Elsevier Inc.",
year = "2013",
doi = "10.1016/j.amc.2013.07.002",
language = "English",
volume = "221",
pages = "522--534",
journal = "Applied Mathematics and Computation",
issn = "0096-3003",
publisher = "Elsevier",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - Calibration of GARCH models using concurrent accelerated random search

AU - Müller, Juliane

AU - Kanniainen, Juho

AU - Piche, Robert

N1 - Contribution: organisation=tta,FACT1=0.5<br/>Contribution: organisation=ase,FACT2=0.5<br/>Portfolio EDEND: 2013-07-29<br/>Publisher name: Elsevier Inc.

PY - 2013

Y1 - 2013

N2 - This paper investigates a global optimization algorithm for the calibration of stochastic volatility models. Two GARCH models are considered, namely the Leverage and the Heston-Nandi model. Empirical information on option prices is used to minimize a loss function that reflects the option pricing error. It is shown that commonly used gradient based optimization procedures may not lead to a good solution and often converge to a local optimum. A concurrent approach where several optimizers (“particles”) execute an accelerated random search (ARS) procedure has been introduced to thoroughly explore the whole parameter domain. The number of particles influences the solution quality and computation time, leading to a trade-off between these two factors. In order to speed up the computation, distributed computing and variance reduction techniques are employed. Tests show that the concurrent ARS approach clearly outperforms the standard gradient based method.

AB - This paper investigates a global optimization algorithm for the calibration of stochastic volatility models. Two GARCH models are considered, namely the Leverage and the Heston-Nandi model. Empirical information on option prices is used to minimize a loss function that reflects the option pricing error. It is shown that commonly used gradient based optimization procedures may not lead to a good solution and often converge to a local optimum. A concurrent approach where several optimizers (“particles”) execute an accelerated random search (ARS) procedure has been introduced to thoroughly explore the whole parameter domain. The number of particles influences the solution quality and computation time, leading to a trade-off between these two factors. In order to speed up the computation, distributed computing and variance reduction techniques are employed. Tests show that the concurrent ARS approach clearly outperforms the standard gradient based method.

U2 - 10.1016/j.amc.2013.07.002

DO - 10.1016/j.amc.2013.07.002

M3 - Article

VL - 221

SP - 522

EP - 534

JO - Applied Mathematics and Computation

JF - Applied Mathematics and Computation

SN - 0096-3003

ER -