RegimeRank: Interpretable Ranking for Sector Rotation
ORIGINAL / Regime-Aware Interpretable Ranking for Sector Rotation
This study proposes RegimeRank, a model that formulates sector rotation as ranking sectors by expected future risk-adjusted active performance, and enhances ranking performance while maintaining interpretability through expert-defined temporal features, macro-regime conditioning, and cross-sector dependency modeling. Its novelty lies in integrating regime awareness with attention mechanisms to provide a diagnosable ranking tool for quantitative portfolio management.
01 ABSTRACT
The authors define sector rotation as ranking sectors by forward sector-benchmark Sharpe ratios and propose RegimeRank, an interpretable model that represents signals via expert-defined temporal characteristics, conditions on learned macro factors via cross-attention, and models cross-sector dependencies via self-attention. On weekly S&P 500 data from 2002 to 2024 under combinatorial purged cross-validation, the model outperforms representative ranking and machine-learning baselines across multiple ranking metrics. Ablation studies support the contributions of latent macro states, regime conditioning, and cross-sector modeling, while attribution and attention analyses illustrate the temporal characteristics, macro states, and sector relationships underlying its rankings.
02 KEY FINDINGS
- RegimeRank represents fundamental and technical signals through expert-defined temporal characteristics and conditions them on learned macro factors via cross-attention.
- The model captures cross-sector dependencies using self-attention and provides interpretability diagnostics through expected-gradient attributions and attention maps.
- On weekly S&P 500 data from 2002 to 2024 under combinatorial purged cross-validation, the model outperforms baselines on multiple ranking metrics.
AI GENERATED SUMMARY / DISCOVERED BY ARXIV CS.LG · ARXIV Q-FIN