Discrete versus continuous parametrization of bank credit rating systems optimization using differential evolution

Kok-Ming Leung, Xi Zhang

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Bank credit rating system is a clustering problem that aims to achieve the optimal classification of the clients' probability of defaults (PDs) into discrete buckets under a number of constraints. This global optimization problem can be parametrized either using continuous or discrete decision variables, and treated using basically the same differential evolution (DE) method that takes into account of real-world constraints imposed by the recent Basel Accord on Banking Supervision. This enables us to make interesting comparisons between continuous versus discrete parametrization of the same problem in terms of the efficiency, robustness and the rate of convergence. It turns out to be beneficial to use discrete parameters for all of these reasons. In addition we have also explored the use of the elitist as well as the classic strategies within the DE approach. The former choice turns out to perform better in terms of efficiency, robustness, and faster convergence, except when the number of required buckets is large.

    Original languageEnglish (US)
    Title of host publicationProceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10
    Pages265-272
    Number of pages8
    DOIs
    StatePublished - 2010
    Event12th Annual Genetic and Evolutionary Computation Conference, GECCO-2010 - Portland, OR, United States
    Duration: Jul 7 2010Jul 11 2010

    Other

    Other12th Annual Genetic and Evolutionary Computation Conference, GECCO-2010
    CountryUnited States
    CityPortland, OR
    Period7/7/107/11/10

    Fingerprint

    Credit Rating
    Differential Evolution
    Parametrization
    Optimization
    Global optimization
    Robustness
    Banking
    Global Optimization
    Rate of Convergence
    Clustering
    Optimization Problem
    Banks

    Keywords

    • Bank credit rating
    • Constraints
    • Differential evolution
    • Integer programming
    • Optimization

    ASJC Scopus subject areas

    • Computational Theory and Mathematics
    • Theoretical Computer Science

    Cite this

    Leung, K-M., & Zhang, X. (2010). Discrete versus continuous parametrization of bank credit rating systems optimization using differential evolution. In Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 (pp. 265-272) https://doi.org/10.1145/1830483.1830531

    Discrete versus continuous parametrization of bank credit rating systems optimization using differential evolution. / Leung, Kok-Ming; Zhang, Xi.

    Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10. 2010. p. 265-272.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Leung, K-M & Zhang, X 2010, Discrete versus continuous parametrization of bank credit rating systems optimization using differential evolution. in Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10. pp. 265-272, 12th Annual Genetic and Evolutionary Computation Conference, GECCO-2010, Portland, OR, United States, 7/7/10. https://doi.org/10.1145/1830483.1830531
    Leung K-M, Zhang X. Discrete versus continuous parametrization of bank credit rating systems optimization using differential evolution. In Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10. 2010. p. 265-272 https://doi.org/10.1145/1830483.1830531
    Leung, Kok-Ming ; Zhang, Xi. / Discrete versus continuous parametrization of bank credit rating systems optimization using differential evolution. Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10. 2010. pp. 265-272
    @inproceedings{bb146ab490dc4124b63b8b596d9a54bb,
    title = "Discrete versus continuous parametrization of bank credit rating systems optimization using differential evolution",
    abstract = "Bank credit rating system is a clustering problem that aims to achieve the optimal classification of the clients' probability of defaults (PDs) into discrete buckets under a number of constraints. This global optimization problem can be parametrized either using continuous or discrete decision variables, and treated using basically the same differential evolution (DE) method that takes into account of real-world constraints imposed by the recent Basel Accord on Banking Supervision. This enables us to make interesting comparisons between continuous versus discrete parametrization of the same problem in terms of the efficiency, robustness and the rate of convergence. It turns out to be beneficial to use discrete parameters for all of these reasons. In addition we have also explored the use of the elitist as well as the classic strategies within the DE approach. The former choice turns out to perform better in terms of efficiency, robustness, and faster convergence, except when the number of required buckets is large.",
    keywords = "Bank credit rating, Constraints, Differential evolution, Integer programming, Optimization",
    author = "Kok-Ming Leung and Xi Zhang",
    year = "2010",
    doi = "10.1145/1830483.1830531",
    language = "English (US)",
    isbn = "9781450300728",
    pages = "265--272",
    booktitle = "Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10",

    }

    TY - GEN

    T1 - Discrete versus continuous parametrization of bank credit rating systems optimization using differential evolution

    AU - Leung, Kok-Ming

    AU - Zhang, Xi

    PY - 2010

    Y1 - 2010

    N2 - Bank credit rating system is a clustering problem that aims to achieve the optimal classification of the clients' probability of defaults (PDs) into discrete buckets under a number of constraints. This global optimization problem can be parametrized either using continuous or discrete decision variables, and treated using basically the same differential evolution (DE) method that takes into account of real-world constraints imposed by the recent Basel Accord on Banking Supervision. This enables us to make interesting comparisons between continuous versus discrete parametrization of the same problem in terms of the efficiency, robustness and the rate of convergence. It turns out to be beneficial to use discrete parameters for all of these reasons. In addition we have also explored the use of the elitist as well as the classic strategies within the DE approach. The former choice turns out to perform better in terms of efficiency, robustness, and faster convergence, except when the number of required buckets is large.

    AB - Bank credit rating system is a clustering problem that aims to achieve the optimal classification of the clients' probability of defaults (PDs) into discrete buckets under a number of constraints. This global optimization problem can be parametrized either using continuous or discrete decision variables, and treated using basically the same differential evolution (DE) method that takes into account of real-world constraints imposed by the recent Basel Accord on Banking Supervision. This enables us to make interesting comparisons between continuous versus discrete parametrization of the same problem in terms of the efficiency, robustness and the rate of convergence. It turns out to be beneficial to use discrete parameters for all of these reasons. In addition we have also explored the use of the elitist as well as the classic strategies within the DE approach. The former choice turns out to perform better in terms of efficiency, robustness, and faster convergence, except when the number of required buckets is large.

    KW - Bank credit rating

    KW - Constraints

    KW - Differential evolution

    KW - Integer programming

    KW - Optimization

    UR - http://www.scopus.com/inward/record.url?scp=77955897299&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=77955897299&partnerID=8YFLogxK

    U2 - 10.1145/1830483.1830531

    DO - 10.1145/1830483.1830531

    M3 - Conference contribution

    AN - SCOPUS:77955897299

    SN - 9781450300728

    SP - 265

    EP - 272

    BT - Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10

    ER -