Reproduce “Beyond ESG Scores: Learning Dynamic Constraints for Sequential Portfolio Optimization” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Xin Li, Yan Ke, Longbing Cao
The authors introduce MACF to estimate add-, hold-, and spillover-risk costs for portfolio moves from point-in-time evidence; MACF-X feeds them to constrained optimizers without changing financial observations or reward. In the US30 2024 backtest, MACF-CRPO reports 31.17% return and 1.74 ESG Violation, versus 31.04% and 1.80 for CRPO, with higher turnover; this does not establish real-world impact or budget feasibility.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.