Essays on novel methods and applications of portfolio optimization
Loading...
URL
Journal Title
Journal ISSN
Volume Title
School of Business |
Doctoral thesis (article-based)
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Authors
Date
Major/Subject
Mcode
Degree programme
Language
en
Pages
40 + app. 100
Series
Aalto University publication series DOCTORAL THESES, 114/2023
Abstract
This dissertation advances the methods and applications of portfolio optimization and consists of two parts. The first part focuses on developing new portfolio optimization methods using drawdown measures. The second part utilizes existing portfolio optimization methods in novel application areas. The first method developed in the dissertation is designed to minimize portfolio drawdown duration, an important criterion institutional investors use. The drawdown duration measure has been discussed in several academic and white papers, but no models that allow for minimizing or controlling drawdown duration in a decision support model are present in the literature. Thus, we cover that research and practice gap and present a new family of portfolio selection models: minimizing maximum drawdown duration, average drawdown duration and tail drawdown duration. The model testing reveals that none of the traditional alternative methods achieve drawdown duration levels close to optimal ones. The second new method, drawdown stochastic dominance, allows for portfolio choice based on comparing random drawdown profiles of investments. Portfolio optimization models exist to minimize drawdown as a single value in the objective function with simplifying assumptions, but no methods account for the whole drawdown distribution. Therefore, we introduce a new variant of the drawdown measure, the corresponding optimization method, and the new dominance rule for portfolio selection in the spirit of second-degree stochastic dominance. Both new methods can readily utilize historical data because they are formulated based on scenarios with discrete returns. The first novel application demonstrates how previously established portfolio optimization models and Monte Carlo simulation methods can be utilized to support portfolio choice in venture capital (VC) markets. The second application study investigates performance enhancements in mixed-asset portfolios (MAPs) by including direct real estate investments (DREIs) in the traditional stock and bond portfolios. Third-degree stochastic dominance (TSD) is applied in the analysis to account for different risk-attitudes. Both DREIs and VC investments may represent an attractive option for investors to diversify risks, but scant studies are available in the literature dedicated to portfolio optimization applications, specifically in these markets.Description
Supervising professor
Liesiö, Juuso, Prof., Aalto University, Department of Information and Service Management, FinlandThesis advisor
Seppälä, Tomi, Dr., Aalto University, FinlandOther note
Parts
- [Publication 1]: Andrei Vedernikov, Juuso Liesiö, Tomi Seppälä. Portfolio Models for Optimizing Drawdown Duration. Working paper, April 2022
- [Publication 2]: Andrei Vedernikov, Juuso Liesiö, Tomi Seppälä. Optimal Portfolio Choice Based on Drawdown Stochastic Dominance. Working paper, April 2022
- [Publication 3]: Andrei Vedernikov, Juuso Liesiö, Tomi Seppälä. Portfolio Optimization model for Supporting Venture Capital Decision-Making. Working paper, April 2022
- [Publication 4]: Andrei Vedernikov. Choice of a Mixed-Asset Portfolio Based on Third-Degree Stochastic Dominance. Working paper, February 2023