This project explores the application of linear algebra, specifically Singular Value Decomposition (SVD), in finance and algorithmic trading. The goal is to create a portfolio of company allocations by analyzing the daily prices of over 1,000 companies. We use SVD to generate the right singular vectors, which are then normalized to form "eigen-portfolios." The process involves training on past data to test the performance of these portfolios.
- Data Import and Preprocessing: Efficiently load and clean large datasets.
- SVD-Based Portfolio Construction: Apply SVD to derive eigenportfolios from return data.
- Portfolio Normalization: Normalize the SVD-derived portfolios for practical implementation.
- Data Visualization: Graphs and charts to visualize key trends in gun violence.
- Python: The main programming language used.
- Pandas & NumPy: For data manipulation and analysis as well as handling large datasets.
- Matplotlib & Seaborn: For creating visualizations of data and results.
- Jupyter Notebook: For running and sharing code.
- Dalila Solis
- Alex Bachrach
- Elena Conway
- Aaron Lo
- Matthew Wilson