Evidence-governed quantitative cyber risk — a trustworthy CLI and scenario engine where every number traces to a reviewed public source.

Cost-sensitive credit card fraud detection on 1.3M transactions. Picks the decision threshold that minimizes expected dollar loss, avoiding $1.25M vs a naive baseline (XGBoost, PR-AUC 0.91). Adds a quant-risk layer (VaR/Expected Shortfall, walk-forward backtesting, PSI drift) and an agentic RAG investigation copilot. Interactive Streamlit app

Sequential comparison of probabilistic forecasts and anytime-valid inference in R.

Cyber Risk Posture Calculator — AI-powered financial exposure estimates for SMBs

Actuarial & quantitative risk portfolio — non-life insurance (GLM, Monte Carlo, Solvency II)

Risk Assessment & Management Labs

Notes on Financial Risk Management by Professor Carol Alexander