INFO 5390
Fairness in Machine Learning
Machine learning is increasingly used in both high-stakes and everyday settings. Yet, its impacts are uneven, often reinforcing existing social hierarchies by disproportionately benefiting some groups while harming others. This course introduces multiple perspectives on fairness in machine learning, spanning domains in predictive and generative AI as well as tabular, image, and text data. Students will develop the skills to identify fairness challenges, understand why they are difficult to address, and reason through strategies for approaching them. Students should have experience coding in Python and have taken at least one introductory course in machine learning or data science.
Topics
- Write code in Python to computationally demonstrate biases in end-to-end algorithmic systems based on choices of data, variables, modeling, and outcomes.
- Apply mathematical definitions of fairness to real-world case studies to explain decisions made by both humans and algorithms.
- Enumerate challenges to practitioners in algorithmic-guided decision-making (including feedback loops, interpretability, and strategic behavior) and explain how these challenges can lead to broader societal impacts.
- Write code in Python to computationally identify fairness issues in machine learning across diverse domains and data types.
- Articulate the key tensions and trade-offs in different machine learning scenarios, and reason about their implications.
- Develop problem-solving strategies to approach fairness challenges that arise in machine learning contexts.
Official roster learning outcomes
Sources
- Course catalogue ↗2026-2027
- Catalogue entry ↗
Catalogue variants
- Fairness in Machine Learning · 3.0 · Graduate