Prototype risk modeling simulation for Portfolio using Arbiter.

Reassessment of P2P Credit Risk Modeling with Macroeconomic Factors

Implémentation d'un modèle de scoring (OpenClassrooms | Data Scientist | Projet 7)

🚗 A dynamic pricing and insurance risk modeling system using Python, XGBoost, SHAP, and DVC. Predicts claim severity and probability, enabling risk-adjusted premium strategies with full reproducibility and CI/CD.

Statistical modeling and simulation project analyzing optimal betting strategies across multi-game sports series using R.

End-to-End Python econometric pipeline for modeling geopolitical risk in international trade using advanced Bayesian filtering, high-dimensional fixed effects, and split-panel jackknife inference. Replicates Hardwick's (2025) methodology with full robustness testing and automated reporting.

Ai-powered hurricane risk assessment model combining loads of data regarding social, climate, infrastructure, and meteorology data.

End-to-end Python notebook that engineers a proxy “bad-client” label, explores drivers of credit risk, and builds a leakage-free XGBoost scorecard with threshold tuning and cross-validation.

Quantitative analysis of macroeconomic indicators and market volatility for investment strategy development

🌍 Model political distance and trade dynamics using a quantitative framework to enhance understanding of international trade relationships.

Monte Carlo risk modeling tool for utility Transmission & Distribution projects

Reusable Python functions and case studies for building internal tools in process development and manufacturing ops

Credit risk assessment using FICO score segmentation, loan default modeling, discretization techniques, and log-likelihood evaluation for predictive analytics in financial services.

High-recall machine learning model to detect SIM swap fraud and system leakage in mobile money transactions.

Quantitative analytic toolkit covering natural gas pricing, storage valuation, loan default risk modeling, and credit rating bucketization, with reusable helpers & visual workflows for pricing and risk teams exploring energy and consumer credit data.

End-to-end Python computational engine for qualitative financial modeling implementing Bočková et al. (2025) methodology. Employs Constraint Satisfaction Problems (CSP) and graph theory to model the impact of rumours on financial systems. Professional-grade codebase with extensive validation and customization capabilities.

Risk-based student loan pricing model with actuarial framework, progressive subsidies, and interactive calculator. -3B annual savings, equity protections for low-income students.

A machine learning project to predict credit risk (GOOD or BAD) for loan applicants using historical loan data from 2007–2014. This solution helps multifinance companies minimize default risk and streamline loan approvals through accurate risk classification and a modern graphical user interface (GUI).

Quantify 2025 Energy Risk & Insurance Case Modeling high-loss CAT events and developing parametric risk triggers to support renewable energy expansion. Includes ML code, writing report, and Presentation.

📈 Analyze how rumors affect investment decisions using a qualitative reasoning engine for better outcomes and informed choices.