Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.00953 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918152495955968 |
|---|---|
| author | Oliva, Christian Tinjala, Silviu Gabriel |
| author_facet | Oliva, Christian Tinjala, Silviu Gabriel |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_00953 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Modeling Market States with Clustering and State Machines Oliva, Christian Tinjala, Silviu Gabriel Computational Engineering, Finance, and Science Machine Learning 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. |
| title | Modeling Market States with Clustering and State Machines |
| topic | Computational Engineering, Finance, and Science Machine Learning |
| url | https://arxiv.org/abs/2510.00953 |