Pairwise Markov Chains for Volatility Forecasting

TL;DR

This paper introduces a novel algorithm for Pairwise Markov Chains that improves continuous value prediction, specifically applied to volatility forecasting, outperforming traditional models like GARCH and neural networks in dynamic regimes.

Contribution

The paper presents a new prediction algorithm for PMC that overcomes feature modeling issues and introduces non-stationarity, enhancing volatility forecasting capabilities.

Findings

PMC with the new algorithm outperforms GARCH(1,1) in volatility prediction.

The approach effectively captures regime changes in financial data.

Enhanced models show improved accuracy across multiple asset pairs.

Abstract

The Pairwise Markov Chain (PMC) is a probabilistic graphical model extending the well-known Hidden Markov Model. This model, although highly effective for many tasks, has been scarcely utilized for continuous value prediction. This is mainly due to the issue of modeling observations inherent in generative probabilistic models. In this paper, we introduce a new algorithm for prediction with the PMC. On the one hand, this algorithm allows circumventing the feature problem, thus fully exploiting the capabilities of the PMC. On the other hand, it enables the PMC to extend any predictive model by introducing hidden states, updated at each time step, and allowing the introduction of non-stationarity for any model. We apply the PMC with its new algorithm for volatility forecasting, which we compare to the highly popular GARCH(1,1) and feedforward neural models across numerous pairs. This is particularly relevant given the regime changes that we can observe in volatility. For each scenario, our algorithm enhances the performance of the extended model, demonstrating the value of our approach.