👋 Hi, I’m Brice Nelson
🧮 Engineer by training, Pythonista by passion, and a quant-in-the-making. I believe the best risk models are like good coffee—strong, refined, and always improving with iteration. ☕
- 🧠 Fintech Projects: Building tools for budgeting, forecasting, and financial planning.
- 📈 Data Science & ML: Applied machine learning projects like credit default prediction and Full Waveform Inversion (FWI) using large-scale seismic datasets.
- 🌐 Full-Stack Development: Flask, PostgreSQL, SQLAlchemy, and Heroku deployments.
- 🧪 Quantitative Modeling: Applying engineering precision and financial logic to data-driven applications—from derivatives modeling to Monte Carlo simulations.
- Languages: Python (the quant powerhouse), SQL
- Frameworks: Flask, FastAPI, SQLAlchemy, Bootstrap, TailwindCSS
- Data Science: Pandas, NumPy, Scikit-learn, DuckDB
- Notebooks & IDEs: Jupyter Lab + JetBrains (DataSpell, PyCharm)—where quants and code come alive
- Databases: PostgreSQL, DuckDB, SQLite
- Cloud & Deployment: Heroku, Vercel, GitHub Pages
- Workflow: Git, GitHub, Conda, Python Virtual Environment
A full-stack budgeting application that allows users to input income, deductions, and track expenses across categories with auto-calculated tax withholding based on state selection. Deployed on Heroku with user registration, profile management, and dynamic dashboards.
- Stack: Python, Flask, PostgreSQL, SQLAlchemy, Bootstrap
- Features: State tax logic, gross income frequency support, user session handling, and dynamic budget projections
A Monte Carlo-powered wealth projection application that simulates retirement readiness based on user inputs like income, expenses, savings rate, and portfolio assumptions. Deployed at: 🌐 www.retireforecast.com
- Stack: Python, Flask, Matplotlib, Heroku
- Features: Simulates thousands of retirement outcomes, visualizes retirement horizon, interactive front-end
- Goal: Help users determine whether their retirement plan is on track or needs adjustment
A machine learning approach to subsurface imaging using seismic waveform data from the OpenFWI dataset. Predicts 2D velocity maps from noisy 4D waveforms. Built with competition constraints and professional-grade documentation.
- Stack: Python, NumPy, Matplotlib, DuckDB, PyTorch (planned)
- Features: Modular codebase, DuckDB metadata layer, full EDA → preprocessing → modeling pipeline
A binary classification model to assess credit default risk using the UCI dataset. Designed with explainability and real-world deployment in mind.
- Focus: EDA, SHAP interpretability, modular pipelines
- Deployment Goal: Flask API + interactive dashboard
A blog-linked repo for my Pencils & Python educational series, where I explore mathematical finance concepts (like derivatives and continuous compounding) using Python.
- Focus: Real-world finance meets code — Black-Scholes, calculus-based modeling, risk metrics
- Blog: Medium: QuantShift
I’m not just building projects—I’m building ecosystems. These are the hubs where I deep-dive into quant finance, data science, and math-driven modeling:
| 🚀 Organization | 🧠 What Happens Here | 🔗 Explore |
|---|---|---|
| Brice Data Science | Experimental ML projects and data science workflows across finance, engineering, and analytics. | Repos » |
| Brice Financial Projects | Fintech applications—budgeting, forecasting, and financial planning tools designed for real-world use. | Repos » |
| QuantShift Lab | Pure quant work: risk models, algorithmic trading strategies, and applied mathematical finance. | Repos » |
| Pencils & Python | Educational repos that blend math, finance, and Python—supporting my Medium blog series. | Repos » |
- 🌐 Portfolio: www.devbybrice.com
- ✍️ Blog: The Quant Shift on Medium
I'm pursuing quant developer and quantitative analyst roles where I can:
- Build and optimize financial models (and make them sing with Python).
- Apply ML & statistical thinking to real market and risk challenges.
- Push code that matters in high-stakes, fast-paced environments.
I’ve engineered both municipal infrastructure and Monte Carlo simulations—because pipelines and portfolios both demand precision. 🏗️ ➔ 📈
📬 brice.web.development@gmail.com | bnelsonemail@icloud.com