Quantitative Risk & Pricing Engine

A collection of Python notebooks that prototype pricing and risk analytics across energy and credit domains. The workflow walks from natural gas price forecasting through storage contract valuation, then shifts to consumer credit default modeling and rating quantization.

Notebooks

• 01_natural_gas_price_forecasting.ipynb – Cleans the natural gas snapshot, fits baseline regression and SARIMAX forecasts, and packages a spot price helper.
• 02_natural_gas_storage_pricing.ipynb – Builds a simple storage contract pricer that replays injection/withdrawal schedules with capacity and cost constraints.
• 03_loan_default_risk_modeling.ipynb – Trains probability-of-default models on borrower data and produces an expected loss calculator.
• 04_credit_rating_quantization.ipynb – Experiments with bucketing strategies to map FICO scores into credit rating tiers.

Data

• Loan_Data.csv – Loan performance dataset used in the credit risk notebooks.
• Nat_Gas.csv – Daily price data powering the natural gas forecasting and storage pricer prototypes.

Environment

These notebooks target Python 3. Create an isolated environment and install the core scientific stack:

python3 -m venv .venv
source .venv/bin/activate
pip install pandas numpy matplotlib scikit-learn statsmodels jupyter

Launch Jupyter to explore or rerun the analysis:

jupyter lab

License

Distributed under the MIT License. See LICENSE for details.