Supervised Classification and Mathematical Optimization

Emilio Carrizosa, Dolores Romero Morales

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

Data mining techniques often ask for the resolution of optimization problems. Supervised classification, and, in particular, support vector machines, can be seen as a paradigmatic instance. In this paper, some links between mathematical optimization methods and supervised classification are emphasized. It is shown that many different areas of mathematical optimization play a central role in off-the-shelf supervised classification methods. Moreover, mathematical optimization turns out to be extremely useful to address important issues in classification, such as identifying relevant variables, improving the interpretability of classifiers or dealing with vagueness/noise in the data.
Data mining techniques often ask for the resolution of optimization problems. Supervised classification, and, in particular, support vector machines, can be seen as a paradigmatic instance. In this paper, some links between mathematical optimization methods and supervised classification are emphasized. It is shown that many different areas of mathematical optimization play a central role in off-the-shelf supervised classification methods. Moreover, mathematical optimization turns out to be extremely useful to address important issues in classification, such as identifying relevant variables, improving the interpretability of classifiers or dealing with vagueness/noise in the data.
LanguageEnglish
JournalComputers & Operations Research
Volume40
Issue number1
Pages150–165
ISSN0305-0548
DOIs
StatePublished - 2013
Externally publishedYes

Keywords

    Cite this

    @article{a671a894592a4ec5a21f49b4fde5ca69,
    title = "Supervised Classification and Mathematical Optimization",
    abstract = "Data mining techniques often ask for the resolution of optimization problems. Supervised classification, and, in particular, support vector machines, can be seen as a paradigmatic instance. In this paper, some links between mathematical optimization methods and supervised classification are emphasized. It is shown that many different areas of mathematical optimization play a central role in off-the-shelf supervised classification methods. Moreover, mathematical optimization turns out to be extremely useful to address important issues in classification, such as identifying relevant variables, improving the interpretability of classifiers or dealing with vagueness/noise in the data.",
    keywords = "Data mining, Mathematical optimization, Support vector machines, Interpretability , Cost efficiency",
    author = "Emilio Carrizosa and Morales, {Dolores Romero}",
    year = "2013",
    doi = "10.1016/j.cor.2012.05.015",
    language = "English",
    volume = "40",
    pages = "150–165",
    journal = "Computers & Operations Research",
    issn = "0305-0548",
    publisher = "Pergamon Press",
    number = "1",

    }

    Supervised Classification and Mathematical Optimization. / Carrizosa, Emilio; Morales, Dolores Romero.

    In: Computers & Operations Research, Vol. 40, No. 1, 2013, p. 150–165.

    Research output: Contribution to journalJournal articleResearchpeer-review

    TY - JOUR

    T1 - Supervised Classification and Mathematical Optimization

    AU - Carrizosa,Emilio

    AU - Morales,Dolores Romero

    PY - 2013

    Y1 - 2013

    N2 - Data mining techniques often ask for the resolution of optimization problems. Supervised classification, and, in particular, support vector machines, can be seen as a paradigmatic instance. In this paper, some links between mathematical optimization methods and supervised classification are emphasized. It is shown that many different areas of mathematical optimization play a central role in off-the-shelf supervised classification methods. Moreover, mathematical optimization turns out to be extremely useful to address important issues in classification, such as identifying relevant variables, improving the interpretability of classifiers or dealing with vagueness/noise in the data.

    AB - Data mining techniques often ask for the resolution of optimization problems. Supervised classification, and, in particular, support vector machines, can be seen as a paradigmatic instance. In this paper, some links between mathematical optimization methods and supervised classification are emphasized. It is shown that many different areas of mathematical optimization play a central role in off-the-shelf supervised classification methods. Moreover, mathematical optimization turns out to be extremely useful to address important issues in classification, such as identifying relevant variables, improving the interpretability of classifiers or dealing with vagueness/noise in the data.

    KW - Data mining

    KW - Mathematical optimization

    KW - Support vector machines

    KW - Interpretability

    KW - Cost efficiency

    U2 - 10.1016/j.cor.2012.05.015

    DO - 10.1016/j.cor.2012.05.015

    M3 - Journal article

    VL - 40

    SP - 150

    EP - 165

    JO - Computers & Operations Research

    T2 - Computers & Operations Research

    JF - Computers & Operations Research

    SN - 0305-0548

    IS - 1

    ER -