Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Credit Risk and Asset Correlation Modelling for the Swedish Market: A Comparative Analysis
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Mathematical Statistics.
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Mathematical Statistics.
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Modellering av kreditrisk och tillgångskorrelationer på den svenska marknaden: En komparativ analys (Swedish)
Abstract [en]

In order to ensure solvency, financial institutions must evaluate their credit risk exposure and determine how much economic capital is required to hold as a cushion. This thesis compares three factor models, namely Asymptotic Single Risk Factor (“ASRF”), Inter-sector and Intra-sector factor models and evaluates how their different characteristics affect the economic capital outcomes. The thesis also investigates how these outcomes are affected when assuming asset dependency through a Student's-$t$ copula. Focus will also be put on how different types and levels of asset correlation affect the models' credit risk results. We use a fictitious loan portfolio consisting of 138 Swedish firms with equity data from between 2007 and 2019 in order to calculate asset correlations and economic capital. Our main findings are that the asset correlations severely impact the outcomes of the credit risk models and that practitioners must calibrate and stress test their models regularly with respect to how correlations vary between different firms. The thesis also finds that using copulas for credit portfolios provides more conservative risk outcomes but makes the models less sensitive to correlation level input.

Abstract [sv]

För att finansiella institutioner ska försäkra sig om att vara solventa måste de utvärdera sin exponering mot kreditrisk och därmed avgöra hur mycket ekonomiskt kapital de behöver hålla som buffert. Denna uppsats jämför tre faktormodeller vid namn Asymptotic Systematic Risk Factor (“ASRF”), Inter-sektor, och Intra-sektor med syfte att undersöka hur deras olika karaktärsdrag påverkar estimaten för ekonomiskt kapital. Vi utvärderar även hur utfallen påverkas av införandet av copula-beroende mellan portföljtillgångarna. Fokus kommer även att läggas på hur olika typer och nivåer av korrelation mellan bolag påverkar de olika modellernas kreditriskutfall. Vi använder oss av en fiktiv låneportfölj bestående av 138 svenska bolag med aktieprisdata mellan 2007 och 2019 för att beräkna korrelationer och ekonomiskt kapital. Uppsatsens främsta resultat pekar på att korrelationerna har en väldigt stor påverkan på det ekonomiska kapitalet och att analytiker rekommenderas att kontinuerligt kalibrera och stresstesta sina modeller med avseende på hur korrelationerna kan skilja sig mellan olika bolag. Vi fann även att copula-beroende gav mycket mer konservativa utfall, det vill säga ett högre ekonomiskt kapital, men var mindre känslig för korrelationsnivåerna mellan bolagen i portföljen.

Place, publisher, year, edition, pages
2019.
Series
TRITA-SCI-GRU ; 2019-070
Keywords [en]
Credit Risk, Economic Capital, Value-at-Risk, Intra-sector correlation, Inter-sector correlation, Copula, Basel III
Keywords [sv]
Kreditrisk, Ekonomiskt kapital, Value-at-Risk, Intra-sektorkorrelation, Inter-sektorkorrelation, Copula, Basel III
National Category
Probability Theory and Statistics
Identifiers
URN: urn:nbn:se:kth:diva-252315OAI: oai:DiVA.org:kth-252315DiVA, id: diva2:1319906
External cooperation
Svedbank AB
Subject / course
Financial Mathematics
Educational program
Master of Science - Industrial Engineering and Management
Supervisors
Examiners
Available from: 2019-06-04 Created: 2019-06-03 Last updated: 2019-06-27Bibliographically approved

Open Access in DiVA

fulltext(1423 kB)55 downloads
File information
File name FULLTEXT01.pdfFile size 1423 kBChecksum SHA-512
7615d0ef64877c33251c143aaf57dd8b19fe4f2199b6855f918f8a7a0445a374b16513fb619e173c125fb09a9d8786f0548a2cc48b493c784e4a4aa57c3b82af
Type fulltextMimetype application/pdf

By organisation
Mathematical Statistics
Probability Theory and Statistics

Search outside of DiVA

GoogleGoogle Scholar
Total: 55 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 222 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf