Papers for

financial risk management teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Statistical gates reduce false positives but limit strategy adoption rates

On the Boundary of Admission Gates: An Injected-Truth Study of Falsification-First Selection in Quantitative Strategy Research

Abstract: Strategy research conflates two problems: finding a profitable rule, and establishing that the finding is not search luck. The latter calls for admission gates -- statistical criteria that must be satisfied before a conclusion is adopted -- yet whether gates work, and at what cost, remains untested. We introduce an injected-truth protocol with a random-admission control that adopts at the same rate as the gate; only if the gate beats this control does it carry information rather than merely raise a threshold. Across synthetic and real-calibrated panels, gates eliminate false discoveries in the weak-signal regime but cut adoption to 1--7%, and add nothing when signals are strong. Most importantly, criteria computed on absolute rather than excess returns silently reject every candidate, including true signals. Keywords: multiple testing, backtest overfitting, strategy admission, injected-truth validation, excess returns, false discovery rate

Tue 6 OctArtificial IntelligenceComputational Engineering, Finance, and Science
The gist
Finding successful strategies can be tricky because sometimes a rule looks good by chance rather than real value. The authors study 'admission gates,' which are rules to decide if a strategy is really good or just lucky. They find these gates work well to stop false findings when signals are weak, but they also reject most strategies, allowing only 1-7% to pass. Interestingly, some common methods wrongly reject all strategies, even the true ones.
Open → 2610.07701v1

Framework guides safe and tracked use of AI in critical workflows

MERCI Cards: An LLM Evaluation and Deployment Framework for High-Stakes Domains

Abstract: As LLMs are increasingly deployed in high-stakes professional workflows, engineers and researchers require principled protocols to systematically track, monitor, and improve model performance across deployment cycles. We present a mathematical framework for iterative LLM evaluation and deployment, and demonstrate its application to AI systems used in criminal justice. Our framework formalizes LLM integration in high-stakes, high-risk, and resource-constrained domains across model selection, rubric design, evaluations and deployment via a weighted multi-objective optimization. We demonstrate that MERCI Cards can guide improvements of the system across deployment iterations, direct developer attention toward under-performing areas, and focus user attention on validation and error-correction in the LLM's outputs.

Sat 3 OctArtificial IntelligenceHuman-Computer Interaction
The gist
Using large language models (LLMs) in important areas like criminal justice is risky and complicated. The paper presents a framework that helps people evaluate, monitor, and improve these AI systems carefully over time. This method uses math to balance different goals like accuracy and resource limits, so developers know where to fix problems and users know when to check results. The framework is designed to keep AI use safer and more reliable in sensitive areas.
Open → 2610.04430v1

Payment fraud detection improves with reflective large language model agent

SR-Fraud: An Outcome-Supervised Reflective LLM Agent Framework for Non-Stationary Payment Fraud Detection

Abstract: Real-time payment fraud detection is a non-stationary streaming prediction problem: adversaries adapt before supervised labels mature, and localized burst attacks can cause losses before retraining. Production systems typically rely on tabular classifiers and rules, which can struggle to capture these emerging sequential patterns before periodic retraining occurs. We present SR-Fraud, an outcome-supervised reflective LLM framework that decouples request-time decisions from offline adaptation. A frozen, stateless agent scores each transaction from a Hybrid Episodic Window to track behavioral shifts, while an offline reflection agent proposes boundary hypotheses from matured errors. A deterministic verifier then admits only supported hypotheses into an executable knowledge state. On a production payment-fraud benchmark, SR-Fraud improves all detection metrics over its frozen decision agent, obtains higher point estimates than static and periodically retrained CatBoost, and detects an emerging fraud burst.

Wed 23 SeptMachine LearningCryptography and Security
The gist
Detecting payment fraud quickly is hard because fraudsters keep changing their tricks, and systems often wait too long to update their rules. The authors propose SR-Fraud, which uses a special kind of AI agent that learns from past mistakes and reflects on patterns without slowing down transactions. This agent can spot sudden bursts of new fraud faster than traditional methods that retrain periodically. Their tests show better fraud detection and faster adaptation on real payment data.
Open → 2609.27287v1