Regime-Switching Fractionally Integrated Asymmetric Power Neural Network Modeling of Nonlinear Contagion for Chaotic Oil and Precious Metal Volatilities

This paper aims at analyzing nonlinear dependence between fractionally integrated, chaotic precious metal and oil prices volatilities. With this respect, the Markov regime-switching integrated asymmetric power versions of generalized autoregressive conditional volatility copula (MS-FIAPGARCH-copula) method are further extended to multi-layer perceptron (MLP)-based neural networks (MS-FIAPGARCH-MLP-copula). The models utilized for modeling daily oil, copper, gold, platinum silver prices, covering a period from 1 January 1990–25 March 2022. Kolmogorov Shannon entropy largest Lyapunov exponents reveal uncertainty chaos. Empirical findings show that: i. network-augmented MS-FIAPGARCH-MLP-copula displayed significant gains in terms forecasts; ii. processes modeled effectively with proposed model, iii. important insights derived method, which highlight tail dependence. Results suggest, given long memory structures, that policy interventions must be kept lowest levels.