Beyond ESG Scores: Learning Dynamic Constraints for Sequential Portfolio Optimization

By Xin Li, Yan Ke, Longbing Cao

Published 2026-05-10

Everscope rating

1518.8

Relevance to quantitative trading

8 / 10

Implementation complexity

7 / 10

Reproducibility

4 / 5

About this paper

Methodology: MACF-X (Multimodal Action-Conditioned Constraint Field with Optimizer-Specific Adapters). Problem types: Portfolio Optimization, Reinforcement Learning, Risk Management, Optimization, Multi-task Learning.

arXiv:2605.09310 · Code · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.