National Repository of Grey Literature 2 records found  Search took 0.00 seconds. 
Mean-Variance and Mean-CVaR Models in Portfolio Optimization
Spousta, Tomáš ; Borovička, Adam (advisor) ; Odintsov, Kirill (referee)
The thesis mainly deals with a comparison of two methods that could be used in portfolio optimization (efficient portfolio frontier searching). The first chapter consists of brief introduction to portfolio theory, it also reveals motivation for usage of more sophisticated risk statistics. Following chapter contains definition of both models that have been used in the analysis. First of them is famous Markowitz's model that has become a legend during 60 years of its existence. The most significant advantage is its simplicity, on the other hand it cannot deal with non-normality of asset returns. Normality assumption can be omitted using Maen-CVaR model -- the second model used in the analysis. Final part of this thesis is an application of both models on four different real datasets. Obtained results are analysed with attention on the constitution of efficient portfolio sets and their VaR.
Portfolio optimization
Večeřa, Jakub ; Borovička, Adam (advisor) ; Fábry, Jan (referee)
Searching of an optimal portfolio -- a suitable diversification of funds among financial instruments is a problem that every investor faces. To find the ideal ratio of assets in an investment you must first choose a suitable theoretical model to represent a portfolio and help predict its future development. Model selection should depend on meeting of its assumptions in current situation. This paper uses Markowitz model and describes how to use the quadratic programming methods, Wolfe algorithm, to get a set of efficient portfolios, the subset of all portfolios from which every rational investor should choose. To generalize and enlarge the role of a set of portfolios, the mentioned procedure is apllied for solving the case of short sale.

Interested in being notified about new results for this query?
Subscribe to the RSS feed.