Quantitative Finance Projects
Below is a portfolio of applied quantitative finance projects that demonstrate expertise in mathematical modeling, data analysis, and algorithmic trading. Source code and visualizations are available in linked files; all projects leverage Python and industry-standard libraries.
-
Option Pricing Models: Developed and simulated asset paths using Brownian motion for Black–Scholes option pricing.
-
Stock Data Analytics and Visualization: Designed static and interactive dashboards (via Streamlit) for visual exploration of major stocks (e.g., MSFT, AAPL), highlighting trends, and time-series dynamics. (datavisual file)
-
Portfolio Optimization: Programmed multi-asset portfolio optimization routines utilizing mean-variance analysis. Implemented both classical weighted approaches and data-driven, real-market inspired algorithms based on reputable quant research channels (https://www.youtube.com/@quantprogram). (portfoliocheck file)
-
Algorithmic Trading Strategies: Backtested systematic momentum and moving average trading systems using Backtrader, evaluating Sharpe ratio, drawdown, and execution performance under transaction costs.
-
Machine Learning in Trading: Applied supervised learning techniques to predict entry/exit points for assets such as MSFT and SPY. The framework includes automated feature engineering and validation on out-of-sample data. Check swing trading approach.
-
Risk management analysis through stop loss.
Some codes were optimized by AI.
Ongoing and Upcoming:
Currently extending machine learning approaches for regime detection and automated market making. Additional projects in high-frequency data modeling and alternative data integration are in progress.