Dynamic Bayesian modeling for risk prediction in credit operations

Hanen Borchani, Ana Maria Martinez, Andres Masegosa, Helge Langseth, Thomas Dyhre Nielsen, Antonio Salmerón, Antonio Fernández, Anders Læsø Madsen, Ramón Sáez

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

4 Citationer (Scopus)
251 Downloads (Pure)

Resumé

Our goal is to do risk prediction in credit operations, and as data is collected continuously and reported on a monthly basis, this gives rise to a streaming data classification problem. Our analysis reveals some practical problems that have not previously been thoroughly analyzed in the context of streaming data analysis: the class labels are not immediately available and the relevant predictive features and entities under study (in this case the set of customers) may vary over time. In order to address these problems, we propose to use a dynamic classifier with a wrapper feature subset selection to find relevant features at different time steps. The proposed model is a special case of a more general framework that can also accommodate more expressive models containing latent variables as well as more sophisticated feature selection schemes.
OriginalsprogEngelsk
TitelThe 13th Scandinavian Conference on Artificial Intelligence (SCAI'2015)
ForlagIOS Press
Publikationsdato2015
Sider17-26
ISBN (Trykt)978-1-61499-588-3
ISBN (Elektronisk)978-1-61499-589-0
DOI
StatusUdgivet - 2015
Begivenhed13th Scandinavian Conference on Artificial Intelligence - Halmstad University, Halmstad, Sverige
Varighed: 4 nov. 20156 nov. 2015
Konferencens nummer: 13th

Konference

Konference13th Scandinavian Conference on Artificial Intelligence
Nummer13th
LokationHalmstad University
LandSverige
ByHalmstad
Periode04/11/201506/11/2015
NavnFrontiers in Artificial Intelligence and Applications
Vol/bind278
ISSN0922-6389

Fingerprint

Feature extraction
Labels
Classifiers

Emneord

    Citer dette

    Borchani, H., Martinez, A. M., Masegosa, A., Langseth, H., Nielsen, T. D., Salmerón, A., ... Sáez, R. (2015). Dynamic Bayesian modeling for risk prediction in credit operations. I The 13th Scandinavian Conference on Artificial Intelligence (SCAI'2015) (s. 17-26). IOS Press. Frontiers in Artificial Intelligence and Applications, Bind. 278 https://doi.org/10.3233/978-1-61499-589-0-17
    Borchani, Hanen ; Martinez, Ana Maria ; Masegosa, Andres ; Langseth, Helge ; Nielsen, Thomas Dyhre ; Salmerón, Antonio ; Fernández, Antonio ; Madsen, Anders Læsø ; Sáez, Ramón. / Dynamic Bayesian modeling for risk prediction in credit operations. The 13th Scandinavian Conference on Artificial Intelligence (SCAI'2015). IOS Press, 2015. s. 17-26 (Frontiers in Artificial Intelligence and Applications, Bind 278).
    @inproceedings{ad89520992bb414fbfb68926b27a3547,
    title = "Dynamic Bayesian modeling for risk prediction in credit operations",
    abstract = "Our goal is to do risk prediction in credit operations, and as data is collected continuously and reported on a monthly basis, this gives rise to a streaming data classification problem. Our analysis reveals some practical problems that have not previously been thoroughly analyzed in the context of streaming data analysis: the class labels are not immediately available and the relevant predictive features and entities under study (in this case the set of customers) may vary over time. In order to address these problems, we propose to use a dynamic classifier with a wrapper feature subset selection to find relevant features at different time steps. The proposed model is a special case of a more general framework that can also accommodate more expressive models containing latent variables as well as more sophisticated feature selection schemes.",
    keywords = "Streaming data, Dynamic Bayesian networks, Variational Bayes, Feature subset selection, Credit operations",
    author = "Hanen Borchani and Martinez, {Ana Maria} and Andres Masegosa and Helge Langseth and Nielsen, {Thomas Dyhre} and Antonio Salmer{\'o}n and Antonio Fern{\'a}ndez and Madsen, {Anders L{\ae}s{\o}} and Ram{\'o}n S{\'a}ez",
    year = "2015",
    doi = "10.3233/978-1-61499-589-0-17",
    language = "English",
    isbn = "978-1-61499-588-3",
    pages = "17--26",
    booktitle = "The 13th Scandinavian Conference on Artificial Intelligence (SCAI'2015)",
    publisher = "IOS Press",

    }

    Borchani, H, Martinez, AM, Masegosa, A, Langseth, H, Nielsen, TD, Salmerón, A, Fernández, A, Madsen, AL & Sáez, R 2015, Dynamic Bayesian modeling for risk prediction in credit operations. i The 13th Scandinavian Conference on Artificial Intelligence (SCAI'2015). IOS Press, Frontiers in Artificial Intelligence and Applications, bind 278, s. 17-26, Halmstad, Sverige, 04/11/2015. https://doi.org/10.3233/978-1-61499-589-0-17

    Dynamic Bayesian modeling for risk prediction in credit operations. / Borchani, Hanen; Martinez, Ana Maria; Masegosa, Andres; Langseth, Helge; Nielsen, Thomas Dyhre; Salmerón, Antonio; Fernández, Antonio; Madsen, Anders Læsø; Sáez, Ramón.

    The 13th Scandinavian Conference on Artificial Intelligence (SCAI'2015). IOS Press, 2015. s. 17-26.

    Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

    TY - GEN

    T1 - Dynamic Bayesian modeling for risk prediction in credit operations

    AU - Borchani, Hanen

    AU - Martinez, Ana Maria

    AU - Masegosa, Andres

    AU - Langseth, Helge

    AU - Nielsen, Thomas Dyhre

    AU - Salmerón, Antonio

    AU - Fernández, Antonio

    AU - Madsen, Anders Læsø

    AU - Sáez, Ramón

    PY - 2015

    Y1 - 2015

    N2 - Our goal is to do risk prediction in credit operations, and as data is collected continuously and reported on a monthly basis, this gives rise to a streaming data classification problem. Our analysis reveals some practical problems that have not previously been thoroughly analyzed in the context of streaming data analysis: the class labels are not immediately available and the relevant predictive features and entities under study (in this case the set of customers) may vary over time. In order to address these problems, we propose to use a dynamic classifier with a wrapper feature subset selection to find relevant features at different time steps. The proposed model is a special case of a more general framework that can also accommodate more expressive models containing latent variables as well as more sophisticated feature selection schemes.

    AB - Our goal is to do risk prediction in credit operations, and as data is collected continuously and reported on a monthly basis, this gives rise to a streaming data classification problem. Our analysis reveals some practical problems that have not previously been thoroughly analyzed in the context of streaming data analysis: the class labels are not immediately available and the relevant predictive features and entities under study (in this case the set of customers) may vary over time. In order to address these problems, we propose to use a dynamic classifier with a wrapper feature subset selection to find relevant features at different time steps. The proposed model is a special case of a more general framework that can also accommodate more expressive models containing latent variables as well as more sophisticated feature selection schemes.

    KW - Streaming data

    KW - Dynamic Bayesian networks

    KW - Variational Bayes

    KW - Feature subset selection

    KW - Credit operations

    U2 - 10.3233/978-1-61499-589-0-17

    DO - 10.3233/978-1-61499-589-0-17

    M3 - Article in proceeding

    SN - 978-1-61499-588-3

    SP - 17

    EP - 26

    BT - The 13th Scandinavian Conference on Artificial Intelligence (SCAI'2015)

    PB - IOS Press

    ER -

    Borchani H, Martinez AM, Masegosa A, Langseth H, Nielsen TD, Salmerón A et al. Dynamic Bayesian modeling for risk prediction in credit operations. I The 13th Scandinavian Conference on Artificial Intelligence (SCAI'2015). IOS Press. 2015. s. 17-26. (Frontiers in Artificial Intelligence and Applications, Bind 278). https://doi.org/10.3233/978-1-61499-589-0-17