← All projects

QRS research · Financial risk · Certified decisions

RiskHedge

Certify the Decision, Not the Shortcut: Fail-Closed Screening for Financial Risk Decisions

Accept a cheap risk computation only when a certificate shows it picks the same hedges as exhaustive evaluation.

The usual shortcut ranks hedges from cheap approximate prices and accepts the result, so near the cut-off a small error can silently change which hedges are chosen. RiskHedge keeps the cheap computation but accepts its answer only when a certificate proves that exhaustive evaluation would choose the same hedges. Otherwise it pays for exact prices or falls back to exact evaluation.

Details
risk (lower is better) →ABCDEFcertified: the top 3 cannot change
Bars are risk intervals: each hedge's exact risk lies somewhere inside its bar. The three lowest are chosen. The gate accepts only when the chosen bars sit entirely left of the rest. After exact repricing the three chosen intervals lie entirely below the other three, so no exact value can change the choice. Illustrative toy, not paper data.

RiskHedge at a glance

The idea

Each candidate hedge j has a risk interval [ℓj,uj] computed from certified price bounds. A proposed top-k set D is accepted only if

(ud,idd)<(ℓe,ide)

for every chosen d∈D and every rejected e∉D. Every chosen hedge is better at its worst than every rejected hedge at its best, so exact repricing cannot change the set; IDs break ties.

Experiments

Synthetic tested

Gate wrong or unsupported0/200
Midpoint shortcut silently wrong10/200
Exact work, median17.2%

200 fresh instances from one synthetic Merton option-hedging pipeline, enriched near the decision boundary. Work is the share of exhaustive exact pricing paid after the initial bounds.

Real portfolios Not yet tested

No real portfolio data has been used yet.

Workshop paper

  • Certify the Decision, Not the Shortcut: Fail-Closed Screening for Financial Risk Decisions

    Yingzhi Tang (Quantitative Research Society, Singapore; The Chinese University of Hong Kong, Shenzhen), Yuhe Sui (Quantitative Research Society, Singapore; Nanyang Technological University)

    Financial AI Security, Privacy, and Safety Workshop (FinAI-SPS) at ICAIF 2026 · poster · non-archival

Accepted Research

  • Diverse Scenarios, Selective Evaluation: Certified Spectral-Risk Decisions under Costly Robustness Tests

    Yuhe Sui, Yingzhi Tang

    EvoRobust Workshop, NeurIPS 2026 · 2026 · Accepted [OpenReview]

Project team

QR code for qrsntu.org/projects/riskhedge/
Scan to open this page