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.

The Bias Assessment Metrics and Measures Repository



The Bias Assessment Metrics and Measures Repository

Currently, there are no repositories that can help in efficiently determining the appropriate metrics or measures to adopt for assessing or evaluating bias in an AI project or AI system. For instance, metrics and measures for audio data used in the recommendation engine are not easily determinable for different components of the AI system and different stages in the process. 

The Bias Assessment Metrics and Measures project aims to compile a comprehensive repository of metrics, measures, and thresholds that AI practitioners can use to assess bias across various stages of the AI development lifecycle. Bias in AI systems can lead to unjust and discriminatory outcomes, making it imperative to have a repository of relevant metrics and measures to assess and address bias effectively. The project will cover a wide range of data types, model types, process stages, and project components to provide a holistic approach to Bias Assessment.

 

You can access the database here - https://shorturl.at/lKNV8

About the tool




Objective(s):


Impacted stakeholders:


Target sector(s):


Country of origin:


Lifecycle stage(s):


Type of approach:




License:




Stakeholder group:


Geographical scope:


Required skills:


Tags:

  • bias mitigation

Modify this tool

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.