Institutional Repository of Vilnius University
Akcijų portfelio rizikos vertinimas taikant VaR ir CVaR metodus /
Abstract
dc:descriptionThis thesis analyses stock portfolio risk assessment using Value-at-Risk (VaR) and Conditional Value-at-Risk (CVaR) methods. VaR and CVaR are among the most widely used financial risk measures, allowing the assessment of potential losses of an investment portfolio. The theoretical part discusses the properties of logarithmic returns, the concept of portfolio return and risk, mathematical definitions of VaR and CVaR, their properties, and the main risk assessment methods: parametric, historical simulation, and Monte Carlo simulation. The empirical part analyses a stock portfolio consisting of five large-cap U.S. companies: Apple (AAPL), Microsoft (MSFT), Amazon (AMZN), JPMorgan Chase (JPM), and Johnson & Johnson (JNJ). The study uses daily closing price data for the period 2021–2025 obtained from the publicly available financial data platform Yahoo Finance. The data are transformed into logarithmic returns, portfolio returns are calculated, and a statistical analysis of portfolio returns is performed. Portfolio risk is assessed using parametric, historical simulation, and Monte Carlo simulation VaR and CVaR methods. The results show that the distribution of portfolio returns has fat tails and an increased probability of very large losses. The highest VaR and CVaR values were obtained using the historical simulation method, which best reflected actual market fluctuations and the probability of larger negative returns. The results indicate that, in the worst market scenarios, average portfolio losses may be significantly higher than those indicated by VaR. Therefore, CVaR provides a more comprehensive assessment of investment portfolio risk and its sensitivity to strong market fluctuations.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Blažulionytė, Ignė,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD308326815&prefLang=en_US