Towards a multi-stakeholder value-based assessment framework for algorithmic systems

  Means Value(s) and Manifestation(s) DT AT DE DS Application (model) Approach Visual elements Additional details
[Y] AI Fairness 3601 ([59]) PERFORMANCE
- False Positive and Negative rates

FAIRNESS
- False Positive and Negative rates across groups
- Debiasing algorithms

NON-DISCRIMINATION
- Analysis of data for potential biases, data quality assessment
    Classifiers: logistic regression, random forest classifier and neural networks   - Bar charts
- Confidence bars
 




Red: descriptive documents specifying whether/how a value manifestation is fulfilled
Blue: strategy for fulfilling value manifestations
Green : complete tool for enabling the fulfillment of value manifestations

DT: Development Team
AT: Auditing Team
DE: Data domain Experts
DS: Decision Subject

Back to “Tailored communication of system-related information”

Back to main page

  1. https://github.com/Trusted-AI/AIF360