Explore the corpus

Find evidence, not just documents.

Search Minerva’s current Findings using transparent hybrid retrieval. Results remain strictly inside the configured corpus.

Hybrid retrieval

Results for “AI for Risk Assessment and Compliance”

30 findings

70match

Finding 82731 source

This paper presents TRIAG, an original framework integrating three Generative AI agents in a Multi-Agent Reinforcement Learning ($MARL$) environment for Financial Risk Compliance ($FRC$). Its novelty lies in adaptive, coordinated agent interaction, surpassing traditional models. The compelling industry evaluation demonstrates significant potential impact on quantitative risk management and regulatory compliance practices.

LexicalMeaningQualityGraph

Matched: assessment, compliance, risk

70match

Finding 82701 source

Researchers unveil TRIAG, a pioneering system using three coordinated Generative AI agents trained with Multi-Agent Reinforcement Learning, dramatically boosting speed, accuracy, and adaptability in financial risk compliance for FinTech organizations.

LexicalMeaningQualityGraph

Matched: assessment, compliance, risk

69match

Finding 82721 source

Despite TRIAGs praised adaptability and referenced answers, limitations include testing in a single organization, use of homogeneous agents, and the need for broader trials, underscoring the importance of human oversight and ongoing improvement.

LexicalMeaningQualityGraph

Matched: assessment, compliance, risk

68match

Finding 82711 source

TRIAGs real-world evaluation, new terminology like 'Tri-Reinforced Infused Generative Agents,' and a governance architecture for agent control mark firsts in regulatory risk management, with industry workshops and a practical chatbot interface demonstrating effectiveness.

LexicalMeaningQualityGraph

Matched: assessment, compliance, risk

64match

Finding 30971 source

Addressing a gap in financial regulation, the paper introduces a unique third-party AI certification framework crucial for risk assessment and compliance. Its innovative integration of regulatory concepts with applied testing is both novel and groundbreaking. A financial case study emphasizes its timely, influential contribution to advancing academic and practical knowledge.

LexicalMeaningQualityGraph

Matched: assessment, compliance, risk

63match

Finding 47251 source

This paper synthesizes governance, risk, compliance, and accountability frameworks for AI agents in law and finance, offering a novel perspective by contextualizing established principles within AI deployment. While not introducing new quantitative models or technical innovations, its originality lies in bridging governance concepts with AI, making it relevant for organizational oversight discussions.

LexicalMeaningQualityGraph

Matched: assessment, compliance, risk

60match

Finding 47221 source

A new framework for governing AI 'agentic systems'which set goals, adapt, and decide independentlyshows traditional software rules fall short, especially in high-stakes sectors like law, finance, and auditing.

LexicalMeaningQualityGraph

Matched: assessment, compliance, risk

60match

Finding 47241 source

Surprisingly, AI can discriminate during processes, not just outcomes, and liability almost always lands on the deployer, not the vendor; the chapter urges layered controls but lacks step-by-step guidance for smaller organizations.

LexicalMeaningQualityGraph

Matched: assessment, compliance, risk

60match

Finding 47231 source

The GPA+IAT model maps agentic system propertiesGoal, Perception, Action, Iteration, Adaptation, Terminationto governance needs, while a five-layer 'governance stack' reveals no single rulebook can ensure safe AI deployment.

LexicalMeaningQualityGraph

Matched: assessment, compliance, risk

52match

Finding 43591 source

FINVAULT presents the first execution-grounded security benchmark for LLM-powered financial agents, uniquely addressing real-world compliance and safety gaps. Featuring 31 regulatory scenarios, 107 vulnerabilities, and 963 test cases, its novel methodology enables rigorous, realistic assessment, offering significant impact for both academic research and industry deployment in financial AI agent safety.

LexicalMeaningQualityGraph

Matched: assessment, compliance, risk

52match

Finding 21381 source

The paper innovatively combines $GNN$ and $\text{XAI}$, delivering a pioneering solution for fraud detection in finance. It captures intricate relational dependencies and real-time anomalies while addressing scalability and regulatory transparency. This novel integration offers valuable insights, promising compelling advancements in quantitative risk management and compliance across diverse financial applications remarkably.

LexicalMeaningQualityGraph

Matched: compliance, risk

52match

Finding 30951 source

Case studies in the financial sector demonstrate auditing evaluating AI systems on fairness, bias, explainability, accountability, and robustness, while pilot programs utilize seven-domain criteria with document reviews and stakeholder interviews.

LexicalMeaningQualityGraph

Matched: assessment, compliance, risk

51match

Finding 30961 source

Introducing novel terms such as 'system-level certification' and 'interim certification framework,' the study reveals audit adaptations yet highlights challenges including complex criteria and extensive preparatory demands that might restrict scalability.

LexicalMeaningQualityGraph

Matched: assessment, compliance, risk

51match

Finding 68531 source

This research introduces a prototype pipeline using lightweight tools such as Flask and cURL, and deploys domain-specific fine-tuning with human oversight and explainable AI, addressing biases while ensuring regulatory compliance.

LexicalMeaningQualityGraph

Matched: assessment, compliance, risk

50match

Finding 30941 source

Researchers propose a groundbreaking third-party, system-level certification framework addressing rapid AI developments regulatory gap, emphasizing interim certification measures for ethical and safe practices across high-impact sectors like finance worldwide adoption.

LexicalMeaningQualityGraph

Matched: assessment, compliance, risk

50match

Finding 63121 source

Authors propose novel adaptive compliance and automated risk analytics definitions merging emerging tech with business strategies, validated through data analysis that underscores efficiency gains, highlights confidentiality challenges, urges research significantly.

LexicalMeaningQualityGraph

Matched: compliance, risk

50match

Finding 63101 source

Integration of BRMS with AI and ML boosts fraud detection rates and cuts manual compliance checks, transforming risk management in financial, insurance, and public sectors with groundbreaking efficiency improvements remarkably.

LexicalMeaningQualityGraph

Matched: compliance, risk

49match

Finding 63131 source

The paper integrates Business Rules Management Systems with AI and machine learning for enhanced risk management, particularly fraud detection and compliance automation. Although leveraging established techniques, it presents incremental advancements that are moderately original yet compelling. Its strategic approach demonstrates fresh perspectives offering significant relevance to quantitative risk management professionals.

LexicalMeaningQualityGraph

Matched: compliance, risk

48match

Finding 59321 source

MNAMs offer a promising solution for regulated credit scoring, combining accuracy with transparency and fairness. Potential applications include credit risk assessment and other regulated financial areas. Future research may explore extending this approach to more flexible architectures and additional regulatory constraints.

LexicalMeaningQualityGraph

Matched: assessment, compliance, risk

48match

Finding 48271 source

Researchers introduce GaMM, a novel hybrid model integrating GARCH representations with an MLP-based mixer, achieving superior high-frequency volatility forecasting, risk assessment, and reducing forecast errors and $VaR$ estimates across models.

LexicalMeaningQualityGraph

Matched: assessment, risk

48match

Finding 21361 source

The research outlines a framework integrating network science, deep learning, and Explainable AI, introducing novel graph modeling of transactional data with crucial indicators like high volumes and node degree metrics.

LexicalMeaningQualityGraph

Matched: compliance, risk

48match

Finding 55321 source

The study highlights the potential of machine learning in improving liquidity risk assessment, suggesting its use in stress-testing and early warning systems. Future research should address data imbalances and expand the methodology to other risk perspectives, enhancing the overall SREP process.

LexicalMeaningQualityGraph

Matched: assessment, risk

48match

Finding 21351 source

Graph Neural Networks, notably Graph Attention Networks, revolutionize fraud detection by capturing hidden transactional relationships and achieving a 91% recall compared to conventional models 72% accuracy in identifying fraudulent schemes.

LexicalMeaningQualityGraph

Matched: compliance, risk

48match

Finding 21371 source

Experimental results demonstrate that GNNs operate efficiently on real-world datasets using mini-batch training and sampling methods, despite challenges regarding computational overhead and diverse data requirements to ensure deployment scalability effectively.

LexicalMeaningQualityGraph

Matched: compliance, risk

47match

Finding 50901 source

AI revolutionizes finance by improving portfolio recommendations, risk management, and automated trading. Future research should address AI's limitations and enhance regulatory oversight. Potential applications include more accurate investment advice, better risk mitigation, and efficient automated trading systems.

LexicalMeaningQualityGraph

Matched: assessment, risk

47match

Finding 83581 source

Presenting a groundbreaking methodology, this paper extracts embeddings from bond holdings data to reveal latent risk characteristics absent from credit ratings and distance-to-default metrics. Employing $PCA$ and $\text{ridge regression}$ within an asset pricing and machine learning framework, the novel approach substantially improves fixed income risk assessment, pricing, and regulatory evaluation.

LexicalMeaningQualityGraph

Matched: assessment, risk

47match

Finding 48301 source

This paper introduces a novel hybrid model that creatively unites traditional GARCH techniques with a multi-layer perceptron architecture $\text{MLP-Mixer}$. Its innovative stacking of MLPs captures temporal and feature dimensions, enhancing prediction accuracy and risk assessment measures. The approach offers fresh perspectives for derivative modeling and volatility forecasting with empirical impact.

LexicalMeaningQualityGraph

Matched: assessment, risk

47match

Finding 68821 source

New research in decentralized finance evaluates six risk management platforms by analyzing quantitative surveys of 138 users and interviews with 12 stakeholders, uncovering strategic innovations enhancing analytics and regulatory compliance.

LexicalMeaningQualityGraph

Matched: compliance, risk

47match

Finding 43561 source

FINVAULT, the first execution-grounded security benchmark for financial AI agents, reveals that leading LLM-powered financial models are alarmingly vulnerable, with compromise rates ranging from 20% to a staggering 85% in complex domains.

LexicalMeaningQualityGraph

Matched: assessment, compliance, risk

47match

Finding 43581 source

The study finds current defenses are impractical, missing many attacks or causing excessive false alarms, and notes FINVAULTs sandboxed tests, while realistic, cannot fully capture the complexity of live financial systems.

LexicalMeaningQualityGraph

Matched: assessment, compliance, risk