The calibration of financial models is laborious, time-consuming and expensive, and needs to be performed frequently by financial institutions. Recently, the application of artificial neural networks (ANNs) for model calibration has gained interest. This paper provides the first comprehensive empirical study on the application of ANNs for calibration based on observed market data. We benchmark the performance of the ANN approach against a real-life calibration framework that is in action at a large financial institution. The ANN based calibration framework shows competitive calibration results, roughly four times faster with less computational efforts. Besides speed and efficiency, the resulting model parameters are found to be more stable over time, enabling more reliable risk reports and business decisions. Furthermore, the calibration framework involves multiple validation steps to counteract regulatory concerns regarding its practical application.

Considering counterparty credit risk (CCR) for derivatives using valuation adjustments (CVA) is a fundamental and challenging task for entities involved in derivative trading activities. Particularly calculating the expected exposure is time consuming and complex. This paper suggests a fast and simple semi-analytical approach for exposure calculation, which is a modified version of the new regulatory standardized approach (SA-CCR). Hence, it conforms with supervisory rules and IFRS 13. We show that our approach is applicable to multiple asset classes and derivative products, and to single transactions as well as netting sets. Keywords Counterparty credit risk • Credit valuation adjustments (CVA) • Credit exposure • Standardized approach for measuring counterparty credit risk exposures (SA-CCR) JEL Classification G21 • G32 The authors would like to thank the participants of the Quantitative Methods in Finance (QMF) Conference 2018 in Sydney for helpful comments. We would also like to thank two anonymous referees for comments which greatly helped us improving the paper.

The calibration of financial models is laborious, time-consuming and expensive, and needs to be performed frequently by financial institutions. Recently, the application of artificial neural networks (ANNs) for model calibration has gained interest. This paper provides the first comprehensive empirical study on the application of ANNs for calibration based on observed market data. We benchmark the performance of the ANN approach against a real-life calibration framework that is in action at a large financial institution. The ANN based calibration framework shows competitive calibration results, roughly four times faster with less computational efforts. Besides speed and efficiency, the resulting model parameters are found to be more stable over time, enabling more reliable risk reports and business decisions. Furthermore, the calibration framework involves multiple validation steps to counteract regulatory concerns regarding its practical application.