Metastable Hidden Markov Processes: a theory for modeling financial markets

Author:

Diego Marcondes, Adilson Simonis

Keyword:

Economics, General Economics, General Economics (econ.GN), Probability (math.PR), Methodology (stat.ME)

journal:

date:

2023-10-18 16:00:00

Abstract

The modeling of financial time series by hidden Markov models has been performed successfully in the literature. In this paper, we propose a theory that justifies such a modeling under the assumption that there exists a market formed by agents whose states evolve on time as an interacting Markov system that has a metastable behavior described by the hidden Markov chain. This theory is a rare application of metastability outside the modeling of physical systems, and may inspire the development of new interacting Markov systems with financial constraints. In the context of financial economics and causal factor investment, the theory implies a new paradigm in which fluctuations in investment performance are primarily driven by the state of the market, rather than being directly caused by other variables. Even though the usual approach to causal factor investment based on causal inference is not completely inconsistent with the proposed theory, the latter has the advantage of accounting for the non-stationary evolution of the time series through the change between hidden market states. By accounting for this possibility, one can more effectively assess risks and implement mitigation strategies.

PDF: Metastable Hidden Markov Processes: a theory for modeling financial markets.pdf