Exploring Fairness in Machine Learning for International Development

Module 3: Pedagogical Framework for Addressing Ethical Challenges

This module introduces a framework for approaching fairness in machine learning, including defining and checking for fairness and considerations when choosing between different fairness implementations.

Objectives

• Provide a framework for approaching issues related to bias in data
• Provide guidance on defining and checking for fairness
• Help students identify how to choose the right technique for the application

Sections

• Protected Attributes and “Fairness through Unawareness”
• Fairness Criteria