I am a researcher and developer affiliated with Rutgers University, specializing in quantitative finance, machine learning, financial risk modeling, and model validation.
My work focuses on designing reproducible analytical systems, developing predictive models, and building independent validation frameworks for complex financial applications. My research interests include central counterparty risk, initial margin modeling, financial econometrics, time-series analysis, deep learning, natural language processing, and responsible artificial intelligence.
An independent validation framework for central counterparty–style initial margin models. The project includes:
- Historical-simulation and parametric Value at Risk models
- Liquidity, concentration, gap-risk, and stress add-ons
- Backtesting and margin-shortfall analysis
- Stress and sensitivity testing
- Procyclicality monitoring
- Benchmark and challenger model comparison
- Model-risk findings and governance documentation
- Automated testing and an interactive monitoring dashboard
A machine learning project focused on financial distress assessment and bank-failure prediction. The project applies statistical and predictive modeling techniques to identify risk indicators associated with institutional instability and bankruptcy.
A quantitative natural language processing project that evaluates Federal Reserve communications, policy narratives, and sentiment indicators. The project investigates how central-bank language may provide information relevant to financial-market analysis.
- Quantitative risk management
- Model development and independent validation
- Central counterparty and initial margin modeling
- Value at Risk and financial stress testing
- Financial econometrics
- Machine learning and deep learning
- Time-series forecasting
- Natural language processing
- Model-risk governance
- Reproducible research and analytical workflows
Programming Languages
Python, R, SQL, PowerShell
Data Science and Machine Learning
pandas, NumPy, SciPy, scikit-learn, statistical modeling, predictive analytics, feature engineering, model evaluation, and explainability
Financial Modeling
Value at Risk, backtesting, stress testing, sensitivity analysis, scenario analysis, volatility modeling, portfolio risk, and procyclicality assessment
Development and Research Tools
Git, GitHub, VS Code, Jupyter Notebook, Google Colab, pytest, Streamlit, YAML, Parquet, and DuckDB
Artificial Intelligence
Deep learning, large language models, retrieval-augmented generation, prompt engineering, AI-assisted analytical workflows, and model-governance documentation
Rutgers University
Research and academic work in applied mathematics, data science, machine learning, and quantitative modeling.
- LinkedIn: [Add LinkedIn Profile URL]
- ORCID: [Add ORCID Profile URL]
- ResearchGate: [Add ResearchGate Profile URL]
I am interested in research and professional collaboration involving quantitative finance, model risk management, machine learning, financial analytics, responsible artificial intelligence, and reproducible computational research.
The repositories presented on this profile are independent research, educational, and portfolio projects. They are not intended for production trading, regulatory compliance, investment advice, or operational risk-management decisions.
“Simulating risk today to secure financial systems tomorrow.”