Automated validation toolkit for tabular ML models in finance and regulated domains.

Experiments using LLMs for whitepater analysis from the AI ML risk management perspective

SR 11-7 & EU AI Act compliant LLM validation framework for financial services — accuracy, adversarial robustness, and explainability auditing with automated report generation.

Institutional Stock Risk Engine & Governance Framework

AI Governance portfolio case study assessing a high-risk automated loan underwriting system using VerifyWise, EU AI Act, NIST AI RMF, and ISO/IEC 42001 concepts.

AI Governance portfolio case study assessing a high-risk automated loan underwriting system using VerifyWise, EU AI Act, NIST AI RMF, and ISO/IEC 42001 concepts.

raucle-detect produces a cryptographic record — the capability receipt — of every action an AI agent takes: what it did, by whose authority, against which independently-verified policy.

End-to-end credit risk modeling: PD/LGD/EL on 1.35M Lending Club loans. Test AUC 0.719, 32 bps portfolio error. Includes drift monitoring, MRM documentation, and live dashboard.

Profile of evidence-bundle-spec scoped to CFPB + OCC + FRB + FDIC readiness across 8 obligation families: model-risk-management + ECOA Reg B + FCRA Reg V + GLBA Safeguards + BSA/AML + Section 1071 + Section 1033 + CFPB UDAAP. FinTech scaffolding, not certification.

Al Governance portfolio case study assessing a high-risk automated loan underwriting system using VerifyWise, EU AI Act, NIST RMF, and ISO/IEC 42001 concepts.

Quantitative diagnostic toolkit for Model Risk Management (MRM). Validates financial regime-switching models for structural stability and ordinal robustness under SR 11-7 and Basel IV governance frameworks.

A Python benchmark for comparing LLM prompting strategies on instruction-following document generation for Model Risk Management validation reports. It evaluates techniques like zero-shot, few-shot, Chain-of-Thought, ReAct, and Reflexion across models using relevancy, completeness, specificity, and error flags such as hallucination.

AWS-oriented AI governance and operations platform for ML and GenAI systems, covering inventory, policy checks, risk scoring, access review, audit evidence, cost monitoring, model monitoring, incidents, model cards, and governance reporting.

Public materials around the Federal Reserve SR 26-2 supervisory letter on Model Risk Management. Falsifiable, cryptographic chain-of-custody spec for AI decisions in regulated financial institutions.

Proyecto integral de calificación crediticia que abarca el desarrollo de modelos, validación, monitorización, calibración, explicabilidad y gobernanza de riesgos utilizando Regresión Logística y XGBoost

Regime model stability diagnostics for SR 11-7 and Basel IV governance

AI governance in regulated industries: the replay imperative — decision record architecture, model registry, and the four actors who will demand accountability

Heterogeneous Expert PLE for financial product recommendation — built with Claude Code, powered by DuckDB. Two Zenodo preprints.

Lightweight AI Governance Risk Assessment tool to score AI models across key risk factors (data quality, bias, privacy, explainability, robustness) with PDF report generation using Streamlit.

CRPTO — Conformal Robust Predict-Then-Optimize. Methodological pair (conformal prediction + robust portfolio optimization) applied to credit risk on Lending Club 2007-2020. Master's thesis paper, Quarto book and reproducible pipeline. Academic single-author, static dataset, not for production.