Credit spread approximation and improvement using random forest regression

DOI10.1016/J.EJOR.2019.02.005MaRDI QIDQ1735198zbMATH OpenOpenAlexFDO

Authors Mathieu Mercadier, Jean-Pierre Lardy

Publication date 28 March 2019

Published in European Journal of Operational Research (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2106.07358

zbMATH Keywords

random forestsfinancerisk analysiscredit default swapsstructural model

Mathematics Subject Classification ID

Derivative securities (option pricing, hedging, etc.) (91G20) Credit risk (91G40)

Abstract: Credit Default Swap (CDS) levels provide a market appreciation of companies' default risk. These derivatives are not always available, creating a need for CDS approximations. This paper offers a simple, global and transparent CDS structural approximation, which contrasts with more complex and proprietary approximations currently in use. This Equity-to-Credit formula (E2C), inspired by CreditGrades, obtains better CDS approximations, according to empirical analyses based on a large sample spanning 2016-2018. A random forest regression run with this E2C formula and selected additional financial data results in an 87.3% out-of-sample accuracy in CDS approximations. The transparency property of this algorithm confirms the predominance of the E2C estimate, and the impact of companies' debt rating and size, in predicting their CDS.

Recommendations

• Predicting credit default swap prices with financial and pure data-driven approaches
• An analytical approximation formula for the pricing of credit default swaps with regime switching
• scientific article; zbMATH DE number 7680756
• Credit risk: simple closed-form approximate maximum likelihood estimator
• Estimation and evaluation of the term structure of credit default swaps: An empirical study

Cites work

• scientific article; zbMATH DE number 3860199 (Why is no real title available?)
• scientific article; zbMATH DE number 1333813 (Why is no real title available?)
• Are financial ratios relevant for trading credit risk? Evidence from the CDS market
• Bagging predictors
• Credit default swaps and systemic risk
• Deep neural networks, gradient-boosted trees, random forests: statistical arbitrage on the S\&P 500
• Do we need hundreds of classifiers to solve real world classification problems?
• Enhancing credit default swap valuation with meshfree methods
• Greedy function approximation: A gradient boosting machine.
• Interdependencies between CDS spreads in the European union: is Greece the black sheep or black swan?
• Liquidity tail risk and credit default swap spreads
• Random forests
• Safety First and the Holding of Assets
• Scikit-learn: machine learning in Python

Cited in

(6)

• Incorporating financial news for forecasting Bitcoin prices based on long short-term memory networks
• A one-sided Vysochanskii-Petunin inequality with financial applications
• Predicting credit default swap prices with financial and pure data-driven approaches
• Cost-Sensitive Extensions for Global Model Trees: Application in Loan Charge-Off Forecasting
• scientific article; zbMATH DE number 7680756 (Why is no real title available?)
• Forecasting gold price with the XGBoost algorithm and SHAP interaction values

Describes a project that uses

Uses Software

• SegNet
• Scikit
• randomForest
• Matplotlib
• NumPy
• Stata

This page was built for publication: Credit spread approximation and improvement using random forest regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1735198)