Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Credit Risk Modeling for European Utility Companies: A Hybrid Approach

Laxdal, Arnar LU and Ásmundsson, Ingi LU (2025) DABN01 20251
Department of Statistics
Department of Economics
Abstract
Assessing credit risk for European utility companies is difficult due to the limited number
of defaults and differences in data availability between firms. This thesis develops a hybrid
framework to estimate one-year Probability of Default for a portfolio of European utilities, combining a
market-based structural model for publicly traded companies with a financial ratio-based
scoring model for private companies. The firms are segmented according to listing status
and business focus (trading vs. non-trading), and the model is calibrated with industry
benchmarks to increase interpretability. The proposed methodology uses the Merton
structural model for firms with equity market data and a tailored financial scorecard
inspired by... (More)
Assessing credit risk for European utility companies is difficult due to the limited number
of defaults and differences in data availability between firms. This thesis develops a hybrid
framework to estimate one-year Probability of Default for a portfolio of European utilities, combining a
market-based structural model for publicly traded companies with a financial ratio-based
scoring model for private companies. The firms are segmented according to listing status
and business focus (trading vs. non-trading), and the model is calibrated with industry
benchmarks to increase interpretability. The proposed methodology uses the Merton
structural model for firms with equity market data and a tailored financial scorecard
inspired by Altman’s Z-score and credit rating agency criteria for firms without market
data. The financial score is mapped to PDs using a calibrated sigmoid function for
conventional utility businesses and a conservative, interval-based assessment for energy
trading firms. All modeling is implemented in Python, employing K-Nearest Neighbors
imputation to address missing data and ensure a complete analysis. The result is an
integrated PD estimation tool suited to the unique characteristics of the utility sector.
This framework fills a gap in the literature by providing a unified, sector-specific approach
to default risk modeling, with clear motivation and contribution: it offers a practical
solution for credit risk evaluation across both public and private entities in an industry
where traditional models fall short. (Less)
Please use this url to cite or link to this publication:
author
Laxdal, Arnar LU and Ásmundsson, Ingi LU
supervisor
organization
course
DABN01 20251
year
type
H1 - Master's Degree (One Year)
subject
keywords
Credit risk, Probability of Default, Merton Model, Altman Z-score, Corporate Default, European Utilities
language
English
id
9198874
date added to LUP
2025-09-12 09:04:34
date last changed
2025-09-12 09:04:34
@misc{9198874,
  abstract     = {{Assessing credit risk for European utility companies is difficult due to the limited number
of defaults and differences in data availability between firms. This thesis develops a hybrid
framework to estimate one-year Probability of Default for a portfolio of European utilities, combining a
market-based structural model for publicly traded companies with a financial ratio-based
scoring model for private companies. The firms are segmented according to listing status
and business focus (trading vs. non-trading), and the model is calibrated with industry
benchmarks to increase interpretability. The proposed methodology uses the Merton
structural model for firms with equity market data and a tailored financial scorecard
inspired by Altman’s Z-score and credit rating agency criteria for firms without market
data. The financial score is mapped to PDs using a calibrated sigmoid function for
conventional utility businesses and a conservative, interval-based assessment for energy
trading firms. All modeling is implemented in Python, employing K-Nearest Neighbors
imputation to address missing data and ensure a complete analysis. The result is an
integrated PD estimation tool suited to the unique characteristics of the utility sector.
This framework fills a gap in the literature by providing a unified, sector-specific approach
to default risk modeling, with clear motivation and contribution: it offers a practical
solution for credit risk evaluation across both public and private entities in an industry
where traditional models fall short.}},
  author       = {{Laxdal, Arnar and Ásmundsson, Ingi}},
  language     = {{eng}},
  note         = {{Student Paper}},
  title        = {{Credit Risk Modeling for European Utility Companies: A Hybrid Approach}},
  year         = {{2025}},
}