Modeling Market States with Clustering and State Machines
This provides a more accurate and interpretable model for financial analysts and investors to understand market regimes and predict returns, though it is incremental as it builds on existing clustering and state machine techniques.
This work tackles the problem of modeling financial markets by introducing an interpretable probabilistic state machine that identifies distinct market states from historical returns, and it shows that this approach significantly outperforms traditional methods in capturing key statistical properties like skewness and kurtosis.
This work introduces a new framework for modeling financial markets through an interpretable probabilistic state machine. By clustering historical returns based on momentum and risk features across multiple time horizons, we identify distinct market states that capture underlying regimes, such as expansion phase, contraction, crisis, or recovery. From a transition matrix representing the dynamics between these states, we construct a probabilistic state machine that models the temporal evolution of the market. This state machine enables the generation of a custom distribution of returns based on a mixture of Gaussian components weighted by state frequencies. We show that the proposed benchmark significantly outperforms the traditional approach in capturing key statistical properties of asset returns, including skewness and kurtosis, and our experiments across random assets and time periods confirm its robustness.