Assessing the risk associated to structured financial products such as collateralized debt obligations, involves processing information about diverse risk factors: some information comes from the different sources directly in aggregated form, therefore it is not possible to estimate the correlation among different risk components. In this paper we address the problem of assessing the credit risk associated to a borrower or to a security by privacy preserving methods. Specifically we suggest use Secure Multiparty Computation to merge the information from the different sources so as to compute more accurately the overall risk profile of securitized assets, without disclosing the information from each individual source.
Privacy preserving risk assessment of credit securities / S. Cimato, E. Damiani, G. Gianini - In: The fifth International conference on signal image technology & Internet based systems : SITIS 2009 : 29 november – 3 december 2009, Marrakesh, Morocco : proceedings / [a cura di] K. Yetongnon, R. Chbeir, A. Dipanda. - Los Alamitos : Institute of electrical and electronics engineers, 2010. - ISBN 9781424457403. - pp. 506-513 (( Intervento presentato al 5. convegno International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) tenutosi a Marakesh, Morocco nel 2009 [10.1109/SITIS.2009.84].
Privacy preserving risk assessment of credit securities
S. CimatoPrimo
;E. DamianiSecondo
;G. GianiniUltimo
2010
Abstract
Assessing the risk associated to structured financial products such as collateralized debt obligations, involves processing information about diverse risk factors: some information comes from the different sources directly in aggregated form, therefore it is not possible to estimate the correlation among different risk components. In this paper we address the problem of assessing the credit risk associated to a borrower or to a security by privacy preserving methods. Specifically we suggest use Secure Multiparty Computation to merge the information from the different sources so as to compute more accurately the overall risk profile of securitized assets, without disclosing the information from each individual source.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.