kth.sePublications
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
Tail Risk Currency Portfolio Optimization
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Probability, Mathematical Physics and Statistics.
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Probability, Mathematical Physics and Statistics.
2024 (English)Independent thesis Basic level (degree of Bachelor of Fine Arts), 10 credits / 15 HE creditsStudent thesisAlternative title
Optimering av tail risk för valutaportföljer (Swedish)
Abstract [en]

In the year 2000 Rockafellar and Uryasev introduced a technique for portfolio optimization which minimizes Conditional Value-at-Risk (CVaR) and calculates Value-at-Risk (VaR) simultaneously as a byproduct of the optimization. This thesis utilizes this method to minimize and compare the CVaR for a portfolio of currencies using two different assumptions of the daily return’s distribution. In the first case, the currencies’ daily returns are modelled as Student’s t-distributed, and normally distributed in the second case. The optimal portfolio weights and corresponding theoretical CVaR and VaR for both distribution assumptions are presented and discussed. Further, the methodology presented in the thesis is backtested, and actual CVaR and VaR are calculated and compared to their theoretical counterparts. The results indicate that the t-distribution models the currencies’ daily returns more accurately and also provides theoretical estimates of CVaR and VaR that are closer to the actual values from the backtested portfolios. However, the portfolios constructed from data sampled from the normal distribution exhibited lower actual VaR and CVaR than the corresponding portfolios from the t-distribution.

Abstract [sv]

År 2000 introducerade Rockafellar och Uryasev en metod för portföljoptimering som minimerar Conditional Value-at-Risk (CVaR) samtidigt som Value-at-Risk (VaR) kan beräknas som biprodukt. Denna rapport använder metoden för att minimera och jämföra CVaR för en portfölj av valutor givet två olika antaganden avseende sannolikhetsfördelningarna för valutakrossarnas dagliga avkastning. I det ena fallet modelleras dessa som t-fördelade, medan de i det andra fallet antas följa en normalfördelning. Optimala portföljvikter tillsammans med tillhörande CVaR och VaR för vardera ansats presenteras och diskuteras. Vidare, utifrån historiskt backtestad data, beräknas portföljernas verkliga CVaR och VaR, vilka jämförs med de teoretiska värdena. Resultaten indikerar att t-fördelningen dels modellerar valutakrossarnas avkastning bättre, dels ger estimat av CVaR och VaR som är närmare portföljens verkliga värden. Däremot var den verkliga VaR och CVaR lägre för portföljerna konstruerade från data samplat från normalfördelningen än för portföljerna för t-fördelningen.

Place, publisher, year, edition, pages
2024.
Series
TRITA-SCI-GRU ; 2024:079
Keywords [en]
Conditional Value at Risk (CVaR), Value at Risk (VaR), portfolio optimization, currencies, tail risk, return distribution
Keywords [sv]
Conditional Value at Risk (CVaR), Value at Risk (VaR), portföljoptimering, valutor, tail risk, avkastningsfördelning
National Category
Probability Theory and Statistics
Identifiers
URN: urn:nbn:se:kth:diva-348235OAI: oai:DiVA.org:kth-348235DiVA, id: diva2:1894634
Subject / course
Applied Mathematics and Industrial Economics
Educational program
Master of Science in Engineering - Industrial Engineering and Management
Supervisors
Examiners
Available from: 2024-09-03 Created: 2024-09-03

Open Access in DiVA

fulltext(1191 kB)121 downloads
File information
File name FULLTEXT01.pdfFile size 1191 kBChecksum SHA-512
94cac89c30dde8a4d7ed515592e0bcd7d19127df38cf4602d6f9c0f6a95b9a10fb263b100bbd9159efbd96605d052731be5bdf2bcd01a9e373d6aa532bb99a23
Type fulltextMimetype application/pdf

By organisation
Probability, Mathematical Physics and Statistics
Probability Theory and Statistics

Search outside of DiVA

GoogleGoogle Scholar
Total: 121 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: 285 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