Portfolio Optimization based on GARCH-EVT-Copula and ARMA-GARCH-EVT-Copula- Forecasting Models

Please enable javascript in your browser.

Gheisari, Iman | 2019

613 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 51571 (44)
University: Sharif University of Technology
Department: Management and Economics
Advisor(s): Zamani, Shiva
Abstract:
In this thesis, we uses GARCH-EVT-copula and ARMA-GARCH-EVT-copula models to perform out-of-sample forecasts and simulate one-day-ahead returns for five stocks of Tehran Stock Exchange. We construct optimal portfolios based on the global minimum variance (GMV), minimum conditional value-at-risk (Min-CVaR) and certainty equivalence tangency (CET) criteria, and model the dependence structure between stock market returns by employing elliptical (Student-t and Gaussian) and Archimedean (Clayton) copulas. We analyze the performances of 42 risk modeling portfolio strategies using out-of-sample back-testing. Our main finding is that the Min-CVaR portfolio, based on ARMA-GARCH-EVT-Clayton forecasts, outperforms the benchmark portfolio based on historical returns. The main goal in this thesis is to find the best prediction model that minimize the risk of investment in a certain portfolio such as portfolio of stocks
Keywords:
General Autoregressive Conditional Heteroskedastic (GARCH) ; Extreme Value Theory ; Copula Functions ; Conditional Value at Risk ; Stock Portfolio Optimization

No TOC