Dynamic Investment Strategies Through Market Classification and Volatility: A Machine Learning Approach
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913775557279744 |
|---|---|
| author | Li, Jinhui Xie, Wenjia Seco, Luis |
| author_facet | Li, Jinhui Xie, Wenjia Seco, Luis |
| contents | This study introduces a dynamic investment framework to enhance portfolio management in volatile markets, offering clear advantages over traditional static strategies. Evaluates four conventional approaches : equal weighted, minimum variance, maximum diversification, and equal risk contribution under dynamic conditions. Using K means clustering, the market is segmented into ten volatility-based states, with transitions forecasted by a Bayesian Markov switching model employing Dirichlet priors and Gibbs sampling. This enables real-time asset allocation adjustments. Tested across two asset sets, the dynamic portfolio consistently achieves significantly higher risk-adjusted returns and substantially higher total returns, outperforming most static methods. By integrating classical optimization with machine learning and Bayesian techniques, this research provides a robust strategy for optimizing investment outcomes in unpredictable market environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02841 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dynamic Investment Strategies Through Market Classification and Volatility: A Machine Learning Approach Li, Jinhui Xie, Wenjia Seco, Luis Portfolio Management Statistics Theory This study introduces a dynamic investment framework to enhance portfolio management in volatile markets, offering clear advantages over traditional static strategies. Evaluates four conventional approaches : equal weighted, minimum variance, maximum diversification, and equal risk contribution under dynamic conditions. Using K means clustering, the market is segmented into ten volatility-based states, with transitions forecasted by a Bayesian Markov switching model employing Dirichlet priors and Gibbs sampling. This enables real-time asset allocation adjustments. Tested across two asset sets, the dynamic portfolio consistently achieves significantly higher risk-adjusted returns and substantially higher total returns, outperforming most static methods. By integrating classical optimization with machine learning and Bayesian techniques, this research provides a robust strategy for optimizing investment outcomes in unpredictable market environments. |
| title | Dynamic Investment Strategies Through Market Classification and Volatility: A Machine Learning Approach |
| topic | Portfolio Management Statistics Theory |
| url | https://arxiv.org/abs/2504.02841 |