Abstract
The purpose of this article is to review the similarity and difference between financial risk minimization and a class of machine learning methods known as support vector machines, which were independently developed. By recognizing their common features, we can understand them in a unified mathematical framework. On the other hand, by recognizing their difference, we can develop new methods. In particular, employing the coherent measures of risk, we develop a generalized criterion for two-class classification. It includes existing criteria, such as the margin maximization and ν-SVM, as special cases. This extension can also be applied to the other type of machine learning methods such as multi-class classification, regression and outlier detection. Although the new criterion is first formulated as a nonconvex optimization, it results in a convex optimization by employing the nonnegative ℓ 1 -regularization. Numerical examples demonstrate how the developed methods work for bond rating.
| Original language | English |
|---|---|
| Pages (from-to) | 365-402 |
| Number of pages | 38 |
| Journal | Computational Management Science |
| Volume | 11 |
| Issue number | 4 |
| DOIs | |
| Publication status | Published - 2014 Sep 27 |
| Externally published | Yes |
Fingerprint
Keywords
- Coherent measures of risk
- Conditional value-at-risk (CVaR)
- Credit rating
- Mean-absolute semi-deviation (MASD)
- ν-Support vector machine (ν-SVM)
ASJC Scopus subject areas
- Management Information Systems
- Information Systems
Cite this
Interaction between financial risk measures and machine learning methods. / Gotoh, Jun ya; Takeda, Akiko; Yamamoto, Rei.
In: Computational Management Science, Vol. 11, No. 4, 27.09.2014, p. 365-402.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Interaction between financial risk measures and machine learning methods
AU - Gotoh, Jun ya
AU - Takeda, Akiko
AU - Yamamoto, Rei
PY - 2014/9/27
Y1 - 2014/9/27
N2 - The purpose of this article is to review the similarity and difference between financial risk minimization and a class of machine learning methods known as support vector machines, which were independently developed. By recognizing their common features, we can understand them in a unified mathematical framework. On the other hand, by recognizing their difference, we can develop new methods. In particular, employing the coherent measures of risk, we develop a generalized criterion for two-class classification. It includes existing criteria, such as the margin maximization and ν-SVM, as special cases. This extension can also be applied to the other type of machine learning methods such as multi-class classification, regression and outlier detection. Although the new criterion is first formulated as a nonconvex optimization, it results in a convex optimization by employing the nonnegative ℓ 1 -regularization. Numerical examples demonstrate how the developed methods work for bond rating.
AB - The purpose of this article is to review the similarity and difference between financial risk minimization and a class of machine learning methods known as support vector machines, which were independently developed. By recognizing their common features, we can understand them in a unified mathematical framework. On the other hand, by recognizing their difference, we can develop new methods. In particular, employing the coherent measures of risk, we develop a generalized criterion for two-class classification. It includes existing criteria, such as the margin maximization and ν-SVM, as special cases. This extension can also be applied to the other type of machine learning methods such as multi-class classification, regression and outlier detection. Although the new criterion is first formulated as a nonconvex optimization, it results in a convex optimization by employing the nonnegative ℓ 1 -regularization. Numerical examples demonstrate how the developed methods work for bond rating.
KW - Coherent measures of risk
KW - Conditional value-at-risk (CVaR)
KW - Credit rating
KW - Mean-absolute semi-deviation (MASD)
KW - ν-Support vector machine (ν-SVM)
UR - http://www.scopus.com/inward/record.url?scp=84919455614&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84919455614&partnerID=8YFLogxK
U2 - 10.1007/s10287-013-0175-5
DO - 10.1007/s10287-013-0175-5
M3 - Article
AN - SCOPUS:84919455614
VL - 11
SP - 365
EP - 402
JO - Computational Management Science
JF - Computational Management Science
SN - 1619-697X
IS - 4
ER -