Robust Portfolio Optimization with Deep Risk Factor Models Under Regime Shifts
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".