Quantitative portfolio optimization framework with market regimes classification, probabilistic time series forecasting, and hidden Markov models

Marcus Oliveira () and Gilson Costa ()
Additional contact information
Marcus Oliveira: Petróleo Brasileiro S.A.-PETROBRAS
Gilson Costa: Rio de Janeiro State University-UERJ

Digital Finance, 2025, vol. 7, issue 3, No 8, 553-603

Abstract: Abstract This paper proposes a three-step top-down methodology for optimizing an investment portfolio. The first step focuses on identifying the best-performing exchange-traded funds from an extensive asset list for each phase of the market cycle. The second step (macro allocation) builds on the first by promoting allocation through the maximization of risk-adjusted returns under uncertainty, utilizing a probabilistic framework. The third step (micro allocation) employs a hidden Markov model approach to characterize the dynamics of asset returns, allowing the application of a mean-variance framework to optimize allocation. The framework also proposes the application of a Generative Adversarial Network to improve risk assessment without prior assumptions about data probabilistic distribution. Experimental results have demonstrated promising risk-adjusted returns, outperforming the S&P 500 benchmark. Additionally, the Micro Allocation approach has proven effective in refining asset weights in stock indices, achieving good performance when applied to IBOVESPA (Brazilian equities index). In particular, all proposed steps individually contribute to improving portfolio performance and can be used together or separately. The framework is sufficiently generic to accommodate various time series forecasting methods with different levels of complexity, as well as to enable integration with fundamentalist approaches.

Keywords: Portfolio optimization; Quantitative methods; Market regimes; Machine learning; Hidden Markov models (search for similar items in EconPapers)
JEL-codes: C15 G11 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s42521-025-00153-4 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:digfin:v:7:y:2025:i:3:d:10.1007_s42521-025-00153-4

Ordering information: This journal article can be ordered from
https://www.springer.com/finance/journal/42521

DOI: 10.1007/s42521-025-00153-4

Access Statistics for this article

Digital Finance is currently edited by Wolfgang Karl Härdle, Steven Kou and Min Dai

More articles in Digital Finance from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().