Catalogue of Tools & Metrics for Trustworthy AI

These tools and metrics are designed to help AI actors develop and use trustworthy AI systems and applications that respect human rights and are fair, transparent, explainable, robust, secure and safe.

Unsupervised bias scan tool



Unsupervised bias scan tool

The tool identifies potentially unfairly treated groups of similar users by an algorithmic-driven decision-support system. The tool returns clusters of users for which the system is underperforming compared to the rest of the data set. The tool makes use of clustering – an unsupervised statistal learning method – to detect anomalies. This means that no data are required on protected attributes of users, e.g., gender, nationality or ethnicity, to detect indirect discrimination, also referred to as multidimensional proxy or intersectional discrimination. The metric by which bias is defined can be manually chosen and is referred to as the bias metric.
 

The tool returns a report which presents the cluster with the highest bias and describes this cluster by the features that characterizes it. This is quantitatively expressed by the (statistically significant) differences in feature means between the identified cluster and the rest of the data. The report also visualizes the outcomes.

Paper: https://arxiv.org/abs/2502.01713

Use Cases

There is no use cases for this tool yet.

Would you like to submit a use case for this tool?

If you have used this tool, we would love to know more about your experience.

Add use case
catalogue Logos

Disclaimer: The tools and metrics featured herein are solely those of the originating authors and are not vetted or endorsed by the OECD or its member countries. The Organisation cannot be held responsible for possible issues resulting from the posting of links to third parties' tools and metrics on this catalogue. More on the methodology can be found at https://oecd.ai/catalogue/faq.