Explore a comprehensive tutorial on using harms and benefits to ground practical AI fairness assessments in finance. Delve into the methodology for evaluating AI systems, focusing on credit scoring case studies and the balance between performance and fairness. Learn about system objectives, confusion matrices, and the importance of personal attributes in AI decision-making. Gain insights into effective system monitoring and review processes to ensure ethical AI implementation in financial contexts.
Implications Tutorial - Using Harms and Benefits to Ground Practical AI Fairness Assessments
Association for Computing Machinery (ACM) via YouTube
Overview
Syllabus
Introduction
Introductions
Overview
Project Background
Project Team
Outputs
Context
Harms and Benefits Approach
Design Goals
Methodology Overview
Intended Uses of the Methodology
The Assessment
Assessment Questions
System Objectives Context
Methodology
Questions Answers
Credit Scoring Case Study
Credit Approval Systems
Confusion Matrices
Part B
Part C
Performance vs Fairness
Personal Attributes
System Monitoring Review
Questions
Taught by
ACM FAccT Conference
