Key takeaways
- IBM has introduced 'AI Fairness 360', an open-source toolkit to identify and address bias in artificial intelligence algorithms.
- The toolkit features nine algorithms designed to mitigate unwanted bias in datasets and machine learning models.
- Bias often arises from prejudiced training data, leading to unfair advantages for privileged groups over unprivileged ones.
- Current tutorials within AIF360 focus on applications such as credit scoring, predicting medical costs, and gender classification in images.
- IBM aims to foster collaboration among researchers through this comprehensive package dedicated to algorithmic fairness.
IBM is launching a new tool which will check biases in algorithms and try to understand how and why they crept in, and how to mitigate them. Called AI Fairness 360 (AIF360), this product by IBM is a comprehensive open-source toolkit of metrics to check for unwanted bias in datasets, machine learning models, and state-of-the-art algorithms.
ML models are increasingly used to make high-stakes decisions about people. Although ML, by its very nature, is always a form of statistical discrimination, the discrimination becomes objectionable when it places certain privileged groups at a systematic advantage and certain unprivileged groups at a disadvantage, says an official release by IBM. Bias in training data, due to either prejudice in labels or under or over-sampling, yields models with unwanted bias.
Reportedly, this initial release of the AIF360 Python package contains nine different algorithms, developed by the broader algorithmic fairness research community, to mitigate that unwanted bias. They can all be called in a standard way, very similar to scikit-learn’s fit or predict paradigm.
AIF360 contains three tutorials as of now. They revolve around:
- Credit scoring
- Predicting medical expenditures
- Classifying face images by gender
Spotted an error? Tell our editors. Read our editorial standards and corrections.





