Welcome to the workshop!
Workshop
In ProgressWelcome to Auditing Fairness and Bias in ML Models
Today's icebreaker:
Fair or Flawed?
Which do you think is harder to detect — performance issues or fairness issues in a model?
What makes one trickier to uncover than the other?
Type your answer in the chat!
Today's agenda:
- Review: Recap key concepts.
- **Practical exercise:**Bias under the microscope.
- **Closing:**Wrap up and reflection.
Today's learning objectives:
- Detect algorithmic bias in model outputs using fairness metrics and explainable AI tools.
- Interpret subgroup disparities using fairness visualisations.
- Recommend mitigation strategies and documentation practices for ethical AI deployment.