Interpretable model ranks stock sectors based on economic regimes
Regime-Aware Interpretable Ranking for Sector Rotation
Machine Learning
Summary
Choosing which parts of the stock market to invest in is tricky because the best sectors change over time and with the economy. The authors created a model called RegimeRank that looks at familiar financial signals and figures out how important they are under different economic conditions. It also understands how different sectors influence each other. Tested on data from 2002 to 2024, this model ranked sectors better than other methods and explains why it makes those rankings.
What this means in practice
- •For portfolio managers: Rank market sectors to guide investment decisions that adapt to changing economic conditions using interpretable signals.
- •For financial data engineers: Build models that integrate economic regimes and sector relationships to improve risk-adjusted ranking of investment opportunities.
Authors
Kelvin J. L. Koa, Ziling Liu, Xinyang Li, Shuowei Feng, Ruoyu Liang, Mathieu Giroux, Eugene Y. Wen, Xuan Yao, Ke-Wei Huang, Hugo Lamarre
Abstract
Sector rotation is a common decision in benchmark-relative portfolio management, where portfolio managers rank sectors for overweight and underweight positions. We formulate this task as ranking sector actions by expected future risk-adjusted active performance, measured with forward sector-benchmark Sharpe ratios. Such rankings should preserve temporal information, express model outputs through economically familiar signal characteristics, account for changes in signal relevance across macroeconomic environments, and capture dependencies among sectors. We propose RegimeRank, an interpretable sector-ranking model that represents fundamental and technical signals through expert-defined temporal characteristics, conditions them on learned macro factors via cross-attention, and models cross-sector dependencies through self-attention. Expected-gradient attributions identify the contributions of individual signal-transformation pairs, while macroeconomic and cross-sector attention maps provide diagnostics of the learned conditioning and relational structure. We evaluate RegimeRank on weekly S&P 500 data from 2002 to 2024 under combinatorial purged cross-validation, where it 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 modelling, while attribution and attention analyses illustrate the temporal characteristics, macro states, and sector relationships underlying its rankings.