Reproduce “Conformal Risk Certificates for Portfolio Optimization Under Uncertainty: A Gated Reinforcement-Learning Approach” 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
Mohammad Zarei, Amirhossein MohammadpourAzari, Moslem Habibi
Gated-CSRC checks proposed portfolios before execution, using timestamped financial text and past prediction errors to set a semantic risk boundary. A learned policy proposes long-only allocations; the gate passes compliant proposals or projects breaches to feasible ones. Across five annual test folds, it records 0.00% observed violations and 11.7% mean annual return, conditional on the study’s calibration assumptions.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.