Market state transitions and crash early warning in the Chinese stock market
Understanding systemic risk in financial markets requires tools that capture both structural complexity and dynamic evolution. This study adopts a complex systems perspective to analyze the Chinese stock market through correlation-based state classification. Using multidimensional scaling and K-mean...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-08-01
|
| Series: | Frontiers in Physics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphy.2025.1647667/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849394013921083392 |
|---|---|
| author | Wu-Yue Pang Wu-Yue Pang Li Lin Li Lin |
| author_facet | Wu-Yue Pang Wu-Yue Pang Li Lin Li Lin |
| author_sort | Wu-Yue Pang |
| collection | DOAJ |
| description | Understanding systemic risk in financial markets requires tools that capture both structural complexity and dynamic evolution. This study adopts a complex systems perspective to analyze the Chinese stock market through correlation-based state classification. Using multidimensional scaling and K-means clustering on rolling stock return correlations, we identify five distinct market states that reflect varying degrees of systemic co-movement and exhibit strong temporal persistence and local transition patterns. We find that transitions among these states encode meaningful information about market structural shifts and are closely linked to the emergence of crash conditions. Building on this insight, we construct an early warning model using decision trees trained on temporal features derived from market state transitions—including medium-term state distributions, directional change ratios, and short-term evolutionary paths. The model achieves high recall and precision across configurations, and supports real-time adaptability via projection-based state labeling. These results highlight the value of market state dynamics and their transitions as a basis for systemic risk monitoring and crash anticipation in complex financial systems. |
| format | Article |
| id | doaj-art-8b2e43f3b2ba45cc8392420437204a5c |
| institution | Kabale University |
| issn | 2296-424X |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physics |
| spelling | doaj-art-8b2e43f3b2ba45cc8392420437204a5c2025-08-20T03:40:13ZengFrontiers Media S.A.Frontiers in Physics2296-424X2025-08-011310.3389/fphy.2025.16476671647667Market state transitions and crash early warning in the Chinese stock marketWu-Yue Pang0Wu-Yue Pang1Li Lin2Li Lin3Department of Finance, Business School, East China University of Science and Technology, Shanghai, ChinaSchool of Information Science and Engineering, East China University of Science and Technology, Shanghai, ChinaDepartment of Finance, Business School, East China University of Science and Technology, Shanghai, ChinaRisk-Center, ETH Zürich, Zürich, SwitzerlandUnderstanding systemic risk in financial markets requires tools that capture both structural complexity and dynamic evolution. This study adopts a complex systems perspective to analyze the Chinese stock market through correlation-based state classification. Using multidimensional scaling and K-means clustering on rolling stock return correlations, we identify five distinct market states that reflect varying degrees of systemic co-movement and exhibit strong temporal persistence and local transition patterns. We find that transitions among these states encode meaningful information about market structural shifts and are closely linked to the emergence of crash conditions. Building on this insight, we construct an early warning model using decision trees trained on temporal features derived from market state transitions—including medium-term state distributions, directional change ratios, and short-term evolutionary paths. The model achieves high recall and precision across configurations, and supports real-time adaptability via projection-based state labeling. These results highlight the value of market state dynamics and their transitions as a basis for systemic risk monitoring and crash anticipation in complex financial systems.https://www.frontiersin.org/articles/10.3389/fphy.2025.1647667/fullmarket state transitionsystemic riskearly warningcorrelation structurestock market |
| spellingShingle | Wu-Yue Pang Wu-Yue Pang Li Lin Li Lin Market state transitions and crash early warning in the Chinese stock market Frontiers in Physics market state transition systemic risk early warning correlation structure stock market |
| title | Market state transitions and crash early warning in the Chinese stock market |
| title_full | Market state transitions and crash early warning in the Chinese stock market |
| title_fullStr | Market state transitions and crash early warning in the Chinese stock market |
| title_full_unstemmed | Market state transitions and crash early warning in the Chinese stock market |
| title_short | Market state transitions and crash early warning in the Chinese stock market |
| title_sort | market state transitions and crash early warning in the chinese stock market |
| topic | market state transition systemic risk early warning correlation structure stock market |
| url | https://www.frontiersin.org/articles/10.3389/fphy.2025.1647667/full |
| work_keys_str_mv | AT wuyuepang marketstatetransitionsandcrashearlywarninginthechinesestockmarket AT wuyuepang marketstatetransitionsandcrashearlywarninginthechinesestockmarket AT lilin marketstatetransitionsandcrashearlywarninginthechinesestockmarket AT lilin marketstatetransitionsandcrashearlywarninginthechinesestockmarket |