Abstract
This paper provides a methodology for valuing credi t default swaps ( CDS ). In these financial instruments a sequence of payments is promised in return for protection again st the credit losses in the event of default. Given the widespread use of credit default swaps, one major concern is wheth er the credit risk has been priced accurately. Cred it risk assessment of counterparty is an area of renewed interest due to the present financial crises. This article proposes a non parametric model for es timating pricing of the CDS, using learning network s, based on the structural approach pioneered by Merton [1] as regards the independent variables; he proposed a model for assessing the credit risk of a company by characteriz ing the company’s equity as a call option on its as sets. The model that we are introducing turns out peculiar not only for the use of the neural network, but also for th e use of the implied volatility of one-year options written on the share s of the analyzed companies, instead of historical volatility: this leads to a higher capability of getting the signals launched by the market about the future creditworthiness of the firm (historic volatility, being a medium value, brings in tempora l lags in the evaluation ). Besides, our analysis differs from the structural approach for the fact that it considers the 30-month mean-reverting historical series for CDS spre ads, and this turns out to be one of the main advantages of our f orward-looking model.
Highlights
In recent years, the market for credit derivatives has expanded dramatically
The model that we are introducing turns out peculiar for the use of the neural network, and for the use of the implied volatility of one-year options written on the shares of the analyzed companies, instead of historical volatility: this leads to a higher capability of getting the signals launched by the market about the future creditworthiness of the firm
Our model differs from the structural approach for the fact that it consider the 30-month historical series for credit default swaps (CDS) spreads: we show that the use of these credit spreads in addition to other inputs, provides a significant improvement in the accuracy of the model
Summary
The market for credit derivatives has expanded dramatically. Credit derivatives are flexible and efficient instruments that enable users to isolate and trade credit risk. As already pointed out, implied volatility has a determining role among the variables; we have obtained a positive correlation with CDS spreads equal to 0.6338 Leverage is another key variable, obtained dividing the face value of the debt of the firm by the total of its liabilities (including the market capitalization),. The paper ends evidencing that, as far as this field of the financial markets is concerned, neural networks constitute a highly valid instrument of calculation: there still does not exist in literature a formula of evaluation for the CDS, able to tie the quoted spreads to the specific underlying variables of each examined firm, and the neural network can, as will be shown, satisfy this lack with high effectiveness, facing the problem of determination of the functional form from a statistical point of view. The paper concludes with a discussion of advantages and limitations of the solution achieved
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
