Completing the Market: Generating Shadow CDS Spreads by Machine Learning

38 Pages Posted: 23 Jan 2020

See all articles by Nan Hu

Nan Hu

Goethe University Frankfurt

Jian Li


Alexis Mayer Cirkel

International Monetary Fund (IMF)

Date Written: December 2019


We compared the predictive performance of a series of machine learning and traditional methods for monthly CDS spreads, using firms' accounting-based, market-based and macroeconomics variables for a time period of 2006 to 2016. We find that ensemble machine learning methods (Bagging, Gradient Boosting and Random Forest) strongly outperform other estimators, and Bagging particularly stands out in terms of accuracy. Traditional credit risk models using OLS techniques have the lowest out-of-sample prediction accuracy. The results suggest that the non-linear machine learning methods, especially the ensemble methods, add considerable value to existent credit risk prediction accuracy and enable CDS shadow pricing for companies missing those securities.

Keywords: Financial crises, Economic conditions, Financial markets, Financial systems, Credit risk, Credit default swaps, Prediction, Machine Learning methods, WP, CDS, test sample, test set, nowcasting, linear regression

JEL Classification: C10, G1, G12, C52, C53, E01, F16, E52, G21

Suggested Citation

Hu, Nan and Li, Jian and Mayer Cirkel, Alexis, Completing the Market: Generating Shadow CDS Spreads by Machine Learning (December 2019). IMF Working Paper No. 19/292. Available at SSRN:

Nan Hu (Contact Author)

Goethe University Frankfurt ( email )

Grüneburgplatz 1
Frankfurt am Main, 60323

Jian Li

Independent ( email )

No Address Available
United States

Alexis Mayer Cirkel

International Monetary Fund (IMF) ( email )

700 19th Street, N.W.
Washington, DC 20431
United States

Here is the Coronavirus
related research on SSRN

Paper statistics

Abstract Views
PlumX Metrics