MODELING INTRADAY PORTFOLIO RISK WITH DYNAMIC COPULAS AND ARTIFICIAL NEURAL NETWORKS

Wing Ki Liu ； Amanda M. Y. Chu ； Mike K. P. So

《Advances in Financial Planning and Forecasting》 10期 (2022/12) Pp. 113-137

https://doi.org/10.6292/AFPF.202212_(10).0005

摘要

The main purpose of this paper is to examine the application of dynamic copulas and artificial neural networks on multivariate intraday returns. The estimation of the parameters is a sequential process. In each of the experiment, we first apply artificial neural networks to estimate a marginal model and then apply dynamic copulas. In applying artificial neural networks, we found that periodicity is important in modeling the degree of freedom. In applying dynamic copulas, we examine whether the correlations are time-varying and what kind of dynamics the correlations exhibit. We found that the correlations for intraday returns are nonlinear and time-varying in two experiments. After applying dynamic copulas and artificial neural networks, we constructed portfolios based on the predicted means and covariance matrices. We found that the portfolios constructed outperform equally weighted portfolios in two experiments.

關鍵字

Business Analytics ； Copula ； Artificial Neural Networks ； Time Varying Dependence ； Vine Decomposition

參考文獻

Abakah, E. J. A., Addo, E., Jr., Gil-Alana, L. A., & Tiwari, A. K. (2021). Re-examination of international bond market dependence: Evidence from a pair copula approach. International Review of Financial Analysis, 74, 101678. doi:10.1016/j.irfa.2021.101678

Al Janabi, M. A. M., Ferrer, R., & Shahzad, S. J. H. (2019). Liquidity-adjusted value-at-risk optimization of a multi-asset portfolio using a vine copula approach. Physica A: Statistical Mechanics and its Applications, 536, 122579. doi:10.1016/j.physa.2019.122579

Almeida, C., Czado, C., & Manner, H. (2016). Modeling high-dimensional time-varying dependence using dynamic D-vine models. Applied Stochastic Models in Business and Industry, 32, 621-638. doi:10.1002/asmb.2182

Apergis, N., Gozgor, G., Lau, C. K. M., & Wang, S. (2020). Dependence structure in the Australian electricity markets: New evidence from regular vine copulae. Energy Economics, 90, 104834. doi:10.1016/j.eneco.2020.104834

Bucci, A. (2020). Cholesky–ANN models for predicting multivariate realized volatility. Journal of Forecasting, 39, 865-876. doi:10.1002/for.2664