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
This bias scan tool identifies potentially unfairly treated groups of similar users. The tool identifies clusters of users that face a higher misclassification rate compared to the rest of the data set. Clustering is an unsupervised ML method, so no data is needed is required on protected attributes of users. The metric by which bias is defined can be manually chosen in advance: False Negative Rate (FNR), False Positive Rate (FPR), or Accuracy (Acc).
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.
About the tool
You can click on the links to see the associated tools
Tool type(s):
Objective(s):
Country of origin:
Lifecycle stage(s):
Type of approach:
Usage rights:
License:
Target groups:
Target users:
Stakeholder group:
Validity:
Enforcement:
People involved:
Required skills:
Tags:
- ai ethics
- trustworthy ai
- validation of ai model
- python
- ai auditing
Use Cases
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