The IEEE P7003 addresses algorithmic bias, emphasizing the need to minimize unintended and unjustified discrimination within algorithm-driven systems. It discusses case studies such as the COMPAS recidivism prediction tool, raising questions about fairness and the impact of algorithms on different social groups. The document outlines key considerations for algorithm development, including the assurance of representativeness and the evaluation of outcomes to mitigate bias.

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
 Person categorization and identifying affected population groups
 Legal frameworks related to Bias
 Psychology of Bias
9
P7003 algorithm development sections
 Algorithmic system design stages
 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