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
[J] Question-driven XAI design ([88]) PERFORMANCE
- Accuracy

FAIRNESS
- Accuracy across groups

TRANSPARENCY
- Disclosure of origin and properties of data

NON-DISCRIMINATION
-Analysis of data for potential biases, data quality assessment

EXPLAINABILITY
- Post-hoc explanations
    Agnostic   - Summary statistics (percentage scores) for data explanations and performance metrics
- Feature importance
- Contrastive explanations
End users were more interested in the limitation of the model: uncertainty




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