Linear Algebra for Financial Data

This project demonstrates how core linear algebra concepts can be applied to real-world financial data using least squares regression.

The jupyter notebook formulates linear regression explicitly as a matrix equation Ax = b and solves it using linear algebra, not black-box machine learning libraries.

This is an educational, beginner-friendly project intended to bridge linear algebra theory and practical data analysis.

Why This Project Is Useful

If you are learning linear algebra and wondering:

• Where does Ax = b show up in real problems?
• What does least squares actually do geometrically?
• How do regression coefficients relate to real data?

This notebook answers those questions with a concrete financial example.

What This Project Does

• Models percentage price change (change_pct) as a linear combination of market features
• Constructs a design matrix (A) and target vector (b)
• Solves an overdetermined system using the least-squares solution
• Interprets regression coefficients in a financial context

The focus is on understanding, not prediction performance.

Who This Project Is For

• Beginners learning linear algebra
• Students applying math to real data for the first time
• Anyone curious how regression emerges from linear algebra