Predicting Credit Default Swap (CDS) Returns with Machine Learning

Authors

  • Terrence (Yidong) Zhang

DOI:

https://doi.org/10.32473/ufjur.v20i1.106275

Abstract

Credit Default Swaps (“CDS”) are contracts that insure one party against default in an underlying financial instrument, usually a bond. Therefore, the price of CDS reflects the perceived risk of default in an underlying financial instrument. This project applied Support Vector Machines (“SVMs”) to the prediction of CDS price changes for several individual companies across time. Previous research applying SVMs to predicting CDS prices used historical CDS prices as model inputs. This project proposed and applied several new input variables. Tests over a period of several years, across a group of CDS time-series, indicate that a combined model which uses the new input variables in addition to historical CDS price changes outperforms models that only use historical CDS price changes.

References

Callen, J. L., Livnat, J., Segal, D. “The Impact of Earnings on the Pricing of Credit Default Swaps.” Accounting Review 84 (2009): 1363-1394

Gündüz, Y., Uhrig-Homburg, M. “Predicting credit default swap prices with financial and pure data-driven approaches.” Quantitative Finance 11.12 (2011): 1709-1727

Huang, Z., Chen, H., Hsu, C., Chen, W., Wu, S. “Credit rating analysis with support vector machines and neural networks: a market comparative study.” Decision Support Systems 37.4 (2004): 543-558

Shin, K., Lee, T., Kim, H. “An application of support vector machines in bankruptcy prediction model.” Expert Systems with Applications 28.1 (2005): 127-135

Van Gestel, T., Baesens, B., Garcia, J., & Van Dijcke, P. “A Support Vector Machine Approach to Credit Scoring.” Bank en Financiewezen 2. (2003): 73-82

Downloads

Published

2018-12-12

Issue

Section

Social & Behavioral Sciences, Business, Education