Machine learning for financial risk management

A framework for estimating Basel IV capital requirements.

A systems-thinking essay arguing that most optimization quietly trades away buffers, slack, and resilience to make present metrics look better. It reframes efficiency as borrowing stability from the future, and shows how education, workforce, infrastructure, markets, and hardware all get optimized into fragility.

The repo contains the main topics carried out in my master's thesis on operational risk. In particular, it is described how to implement the so called Loss Distribution Approach (LDA), which is considered the state-of-the-art method to compute capital charge among large banks.

A quantitative framework for modeling Operational Risk Capital under Basel III standards using the Loss Distribution Approach (LDA). Implements Monte Carlo convolution of Poisson frequency and Generalized Pareto (Heavy-Tailed) severity distributions to calculate the 99.9% Value at Risk (VaR).

⚖️ Explore how optimizing systems can borrow stability from the future, emphasizing resilience and balance over short-term gains.

Operational risk Monte Carlo (Poisson/Lognormal) for collision losses—methods, R code, and 99.9% capital estimate.

Analytical portfolio demonstrating transaction monitoring, judgment-based alert review, and Excel-driven risk analysis to support fraud detection and regulator-safe KYC operations.

Operational risk intelligence that detects when system reality drifts from assumptions over time.