Fairlearn is a Python package that empowers developers of artificial intelligence (AI) systems to assess their system's fairness and mitigate any observed unfairness issues. Fairlearn contains mitigation algorithms as well as metrics for model assessment. Besides the source code, this repository also contains Jupyter notebooks with examples of Fairlearn usage. An AI system can behave unfairly for a variety of reasons. In Fairlearn, we define whether an AI system is behaving unfairly in terms of its impact on people – i.e., in terms of harm. Fairness of AI systems is about more than simply running lines of code. In each use case, both societal and technical aspects shape who might be harmed by AI systems and how. There are many complex sources of unfairness and a variety of societal and technical processes for mitigation, not just the mitigation algorithms in our library.
Features
- Quality-of-service harms
- Documentation available
- Examples available
- Allocation harms
- Metrics for assessing which groups are negatively impacted by a model
- Algorithms for mitigating unfairness