3 credits
Fall 2026 Lecture Upper Division
This course introduces students to how modern data science and machine learning tools are used in finance. We explore how these methods can help us understand markets, forecast returns, and improve investment decisions. The course is applied and emphasizes hands-on coding and empirical analysis rather than formal theorem-proof development. Students will gain practical experience with financial datasets and Python programming, learning to use algorithms responsibly and interpret their results in a financial context.
Learning Outcomes1Analyze financial datasets to identify patterns in returns, volatility, and risk.
2Apply machine learning techniques--such as regularization, dimension reduction, and nonlinear models--to build and evaluate predictive models for financial data.
3Construct and assess factor models and portfolio strategies using ML-based tools, demonstrating understanding of model performance, overfitting, and interpretability.
4Implement Python-based workflows to clean, visualize, and model financial and text-based data, documenting code and methodology clearly.
5Evaluate the trade-offs between model complexity and interpretability when applying ML methods to real financial problems.
Prerequisites
Restrictions
made by Purdue students.