Search for the optimal branching structure from paired copulas when forming an investment portfolio
- 10.2991/iscde-19.2019.33How to use a DOI?
- copula, pair-copula construction, international diversification, stock portfolio management
The article is devoted to the problem of modeling the stock returns of companies in various industry and country affiliations. The main attention is paid to comparison of two methods of structuring a constructure from paired copulas: the maximum spanning tree method and the author's method, which involves the use of industry and country stock indices. The use of stock indices in structuring a constructure from paired copulas allows one to identify the systemic risk component and reduce the impact of temporary false correlations between assets on investment decisions made. Comparison of the effective boundaries of portfolios built using different profitability models showed the advantage of double copula designs compared to simple Archimedean copulas. The results of the Kupiec test testify that the author’s method of structuring the yield model allows one to obtain more conservative risk assessments of the investment portfolio in comparison with the maximum spanning tree method. As part of testing two strategies for optimizing an investment portfolio over a sufficiently long period of time, it was shown that the author’s method of structuring a constructure from paired copulas allows an investor to receive a greater accumulated income. The results will be useful to portfolio managers, as well as private investors using quantitative methods in managing their investment portfolio.
- © 2019, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - E.G. Knyazeva AU - V.A. Tatyannikov AU - D.V. Kandaurov PY - 2019/12 DA - 2019/12 TI - Search for the optimal branching structure from paired copulas when forming an investment portfolio BT - Proceedings of the International Scientific and Practical Conference on Digital Economy (ISCDE 2019) PB - Atlantis Press SP - 839 EP - 845 SN - 2352-5428 UR - https://doi.org/10.2991/iscde-19.2019.33 DO - 10.2991/iscde-19.2019.33 ID - Knyazeva2019/12 ER -