Presentation at the TU Delft - IEEE workshop on Incorporating Ethical Considerations in Autonomous & Intelligent Systems (A/IS), June 2018

1. IEEE P7003 Algorithmic Bias
Considerations
Minimize unintended, unjustified and unacceptable algorithmic bias
Ansgar Koene, Dr. Ir.
The Hague, 11 June 2018

2. Algorithmic Discrimination
2

3. Confirmation Bias: Predictive policing
3
 A need for counterfactual double blind trials

4. Complex individuals reduced to
simplistic binary stereotypes
4

5. Case study: Recidivism risk prediction
 COMPAS recidivism prediction tool
– Built by a commercial company, Northpointe, Inc.
 Estimates likelihood of criminals re-offending in future
– Inputs: Based on a long questionnaire
– Outputs: Used across US by judges and parole officers
 Are COMPAS’ estimates fair to salient social groups?
5
Machine Bias: There’s software used across the
country to predict future criminals. Propublica

6. Case study: Recidivism risk prediction
6
Is the algorithm fair
to all groups?
When base rates differ, no non-trivial solution can achieve similar FPR,
FNR, FDR, FOR!

7. 7
Open invitation to join the P7003 working group
http://sites.ieee.org/sagroups-7003/

8. Key question when developing or
deploying an algorithmic system
8
 Who will be affected?
 What are the decision/optimization criteria?
 How are these criteria justified?
 Are these justifications acceptable in the context where the system is
used?

9. P7003 foundational sections
 Taxonomy of Algorithmic Bias
 Legal frameworks related to Bias
 Psychology of Bias
 Cultural aspects
9
P7003 algorithm development sections
 Algorithmic system design stages
 Person categorization and identifying affected population groups
 Assurance of representativeness of testing/training/validation data
 Evaluation of system outcomes
 Evaluation of algorithmic processing
 Assessment of resilience against external manipulation to Bias
 Documentation of criteria, scope and justifications of choices

10. Thank You!
10