Chaos Measure Dynamics in a Multifactor Model for Financial Market Predictions
Communications in Nonlinear Science and Numerical Simulation Available online 2 December 2023, 107760
35 Pages Posted: 20 Oct 2022 Last revised: 4 Dec 2023
There are 2 versions of this paper
Chaos Measure Dynamics in a Multifactor Model for Financial Market Predictions
Co-Integrated Chaos Measure Dynamics in a Multifactor Model for Financial Market Predictions
Date Written: September 13, 2022
Abstract
Abstract. To answer the question if chaos changes over time, we apply rolling windows to wavelet-denoised logarithmic S&P500 returns (2000-2020) and calculate consecutive chaos measures (e.g., Hurst-, maximum Lyapunov exponent or sample entropy). We state time-variation of the chaos measure series, indicating chaos instability or inherent chaotic time variations of the underlying (hyper-) chaotic deterministic S&P500 return system. Moreover, we indent to use these chaos measure series as predictors for the denoted financial series. An optimised selection of these series is used as input features for a dynamic factor model realised as deep learning multilayer perception neural network to predict the original S&P500 price and return series out-of-sample. The approach is validated by performance metrics (e.g., explained variance score) and the residuals are shown to be non-autocorrelated and ~iid. Finally, we compare the results with selected base or benchmark models (e.g., autoregressive models). Thus, the approach provides a novel multifactor model for practical market price predictions from a dynamical (inherent) system-based view.
Keywords: time-varying chaos, chaos instability, dynamic factor model, deep learning neural network financial predictions, financial market predictions
JEL: G1, C01, C02, C22, C18
MSC: 65P20, 37N30, 65P40, 91-10
Keywords: time-varying chaos, chaos instability, dynamic factor model, deep learning neural network financial predictions, financial market predictions
JEL Classification: G1, C01, C02, C22, C18
Suggested Citation: Suggested Citation