Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/153975
Title: AMBIGUOUS RISK MEASURES AND PIECEWISE LINEAR UTILITY MODELS IN PORTFOLIO MANAGEMENT
Authors: JOLINE ANN VILLARANDA UICHANCO
Keywords: Robust portfolio optimization
Optimized Certainty Equivalent
Ambigu-ous Risk Measures
convex risk measure
Issue Date: 2007
Citation: JOLINE ANN VILLARANDA UICHANCO (2007). AMBIGUOUS RISK MEASURES AND PIECEWISE LINEAR UTILITY MODELS IN PORTFOLIO MANAGEMENT. ScholarBank@NUS Repository.
Abstract: Portfolio optimization is the problem of finding a feasible trading strategy that maxi- mizes the expected utility of an investor. A fundamental assumption in this approach is the complete knowledge of the distribution of returns. This assumption is often un-reasonable in practice, where only partial information about the distribution of returns is known or predictable with accuracy. This issue is addressed by a robust optimization approach, where the trading strategy is derived while taking into account the model uncertainty. In this paper, we address the distribution ambiguity by assuming that the returns belong to the family of distributions satisfying known mean, covariance and support information. The investor's utility is modeled as a piecewise-linear concave utility function. We provide conic programming formulations for the robust portfolio optimization problem under mean, covariance and support information. We also provide connections with a new convex risk measure, similar to the optimized certainty equivalent (OCE) risk measure of Ben-Tal and Teboulle [7]. Through computational experiments, we show that our approach derives optimal trading strategies that are robust across di®erent investment horizons.
URI: https://scholarbank.nus.edu.sg/handle/10635/153975
Appears in Collections:Master's Theses (Restricted)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Joline Ann Villaranda Uichanco_thesis_JolineUichanco.pdf252.66 kBAdobe PDF

RESTRICTED

NoneLog In

Page view(s)

1
checked on Jul 10, 2020

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.