Credit default swap pricing using artificial neural networks

Abstract

The credit derivatives market has experienced unprecedented growth over the past few years. As such, there is a growing interest in tools for pricing the most prominent credit derivative, the credit default swap. In this paper, we present several artificial neural networks that predict real-world credit default swap prices. In addition to the input parameters used by analytical pricing strategies, these networks explore the use of historic credit default swap prices and equity prices. It was found that the inclusion of historic parameters has increased the accuracy of the network's prediction of credit default swap prices. 2010 IEEE.