Fast Bayesian Calibration of Option Pricing Models Based on Sequential Monte Carlo Methods and Deep Learning.

Model calibration is a challenging yet fundamental task in financial engineering. Using sequential Monte Carlo methods, we reformulate the nonconvex optimization problem as a Bayesian estimation task. This allows to compute any statistic of the estimated parameters, mitigating the strong dependence...

Descripción completa

Detalles Bibliográficos
Publicado en:Journal of Financial Econometrics Vol. 24; no. 3; pp. 1 - 25
Autores principales: Brignone, Riccardo, Gonzato, Luca, Knaust, Sven, Lütkebohmert, Eva
Formato: Artículo
Publicado: Oxford University Press / USA 2026
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=194637004&site=ehost-live
header:
  @attributes:
    shortDbName: ssf
    uiTerm: 194637004
    longDbName: Social Sciences Full Text (H.W. Wilson)
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        14798409
        T2Y
      jtl: Journal of Financial Econometrics
      issn: 14798409
      maglogo: N
    pubinfo:
      dt: 2026
      vid: 24
      iid: 3
      pid: 622
      pub: Oxford University Press / USA
    artinfo:
      ui:
        194637004
        10.1093/jjfinec/nbag011
      ppf: 1
      ppct: 24
      formats:
      tig:
        atl: Fast Bayesian Calibration of Option Pricing Models Based on Sequential Monte Carlo Methods and Deep Learning.
      aug:
        au:
          Brignone, Riccardo
          Gonzato, Luca
          Knaust, Sven
          Lütkebohmert, Eva
        affil:
          Department of Economics and Management, University of Pavia, Pavia, Italy
          Department of Statistics and Operations Research, University of Vienna, Vienna, Austria
          Department of Economics, University of Freiburg, Freiburg i. Br, Germany
      su:
        Monte Carlo method
        Bayes' estimation
        Standard & Poor's 500 Index
        Markov chain Monte Carlo
        Financial engineering
        Deep learning
        Artificial neural networks
      sug:
        subj:
          Monte Carlo method
          Bayes' estimation
          Standard & Poor's 500 Index
          Markov chain Monte Carlo
          Financial engineering
          Deep learning
          Artificial neural networks
      keyword:
        Bayesian estimation
        C45
        C58
        C61
        C63
        copyrightHolder:Oxford University Press
        copyrightYear:2026
        deep learning
        finance
        G13
        inLanguage:en
        option pricing models
        publisher:Oxford University Press
        sameAs:https://dx.doi.org/10.1093/jjfinec/nbag011
        sequential Monte Carlo
        Bayesian estimation
        C45
        C58
        C61
        C63
        copyrightHolder:Oxford University Press
        copyrightYear:2026
        deep learning
        finance
        G13
        inLanguage:en
        option pricing models
        publisher:Oxford University Press
        sameAs:https://dx.doi.org/10.1093/jjfinec/nbag011
        sequential Monte Carlo
      ab: Model calibration is a challenging yet fundamental task in financial engineering. Using sequential Monte Carlo methods, we reformulate the nonconvex optimization problem as a Bayesian estimation task. This allows to compute any statistic of the estimated parameters, mitigating the strong dependence on starting points and avoiding the troublesome local minima, that plague standard calibration methods. To accelerate computation, we incorporate Markov chain Monte Carlo methods with delayed acceptance and a neural network-based option pricing approach. When applied to S&P 500 index options, our Bayesian algorithms significantly outperform the standard approach in terms of runtime, accuracy, and statistical fit.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: N
    holdings:
      @attributes:
        islocal: N