Forecast combination approach in the loss given default estimation

ABSTRACT

This paper examines a novel method of including macroeconomic variables into Loss Given Default models. The approach is transparent, and it easily translates changes in the overall credit environment into Expected Loss estimates, which is one of the crucial points that was recently introduced in the International Financial Reporting Standard 9. We propose a forecast combination procedure that separates the contract-based variables from the macroeconomic indicators. Two models are prepared and benchmarked to a single ordinary least-squares (OLS) model. To combine the forecasts we use three approaches: simple average, the Granger–Ramanathan Method, and Mallows Model Averaging. We tested our predictions on out-of-time data and found that the forecast combination outperforms the single OLS model in terms of the selected forecast quality metrics.

KEYWORDS:

• Loss given default
• forecast combination
• IFRS 9
• model averaging
• loan loss provisioning

JEL CLASSIFICATION:

• C51
• C53
• G32

Disclosure statement

No potential conflict of interest was reported by the author.

Notes

¹ To assess the robustness, we also compared the following periods: 2010–2014 vs. 2015–2018 and 2010–2016 vs. 2017–2018. The conclusions remain the same.

² To be fully compliant, we also estimated the forecast combination approach only using variables included in the one-stage OLS. The conclusions are the same; the results are available upon request.