Robust Portfolio Optimization with Deep Risk Factor Models Under Regime Shifts
International Journal of Computational and Biological Sciences · 31.12.2025 · 2 (02) · 252-260
DOI: 10.66238/ijcbs30 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computational and Biological Sciences, online erschienen am 31.12.2025. Verfasst von Scott Rodriguez. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Modern portfolio management faces significant challenges arising from the non-stationary nature of financial markets, particularly during periods of structural breaks or regime shifts. Traditional factor models, while mathematically elegant, often fail to capture non-linear dependencies and struggle to adapt rapidly to changing market conditions. This paper proposes a novel framework for robust portfolio optimization that integrates Deep Learning for non-linear factor extraction with regime-switching logic to handle market uncertainty. We introduce a temporal Deep Latent Factor Model based on Temporal Convolutional Networks (TCNs) to disentangle idiosyncratic risk from systematic risk factors in a high-dimensional feature space. These latent factors serve as inputs to a Hidden Markov Model (HMM) that dynamically identifies market regimes. Subsequently, we formulate a distributional robust optimization problem where the ambiguity set is constrained by the Wasserstein distance, centered around the regime-dependent empirical distribution. This approach mitigates the estimation error inherent in mean-variance optimization and provides resilience against worst-case scenarios. Our empirical analysis, conducted on S&P 500 constituents over a twenty-year horizon, demonstrates that the proposed method significantly outperforms traditional benchmarks and state-of-the-art deep learning baselines in terms of Sharpe ratio and maximum drawdown control.
Zitieren
APA
Rodriguez, S. (2025). Robust Portfolio Optimization with Deep Risk Factor Models Under Regime Shifts. International Journal of Computational and Biological Sciences, 2(02), 252-260. https://doi.org/10.66238/ijcbs30
Vancouver
Rodriguez S. Robust Portfolio Optimization with Deep Risk Factor Models Under Regime Shifts. International Journal of Computational and Biological Sciences. 2025;2(02):252-260. doi:10.66238/ijcbs30
BibTeX
@article{Rodriguez2025,
author = {Rodriguez, Scott},
title = {Robust Portfolio Optimization with Deep Risk Factor Models Under Regime Shifts},
journal = {International Journal of Computational and Biological Sciences},
year = {2025},
volume = {2},
number = {02},
pages = {252--260},
doi = {10.66238/ijcbs30}
}
EUVIMED