Artificial intelligence algorithms have been used to enhance a wide variety of products and services, including assisting human decision making in high-stake contexts. However, these algorithms are complex and have trade-offs, notably between prediction accuracy and fairness to population subgroups. This makes it hard for designers to understand algorithms and design products or services in a way that respects users' goals, values, and needs. We proposed a method to help designers and users explore algorithms, visualize their trade-offs, and select algorithms with trade-offs consistent with their goals and needs. We evaluated our method on the problem of predicting criminal defendants' likelihood to re-offend through (i) a large-scale Amazon Mechanical Turk experiment, and (ii) in-depth interviews with domain experts. Our evaluations show that our method can help designers and users of these systems better understand and navigate algorithmic trade-offs. This paper contributes a new way of providing designers the ability to understand and control the outcomes of algorithmic systems they are creating.
|Original language||English (US)|
|Title of host publication||DIS 2020 - Proceedings of the 2020 ACM Designing Interactive Systems Conference|
|Publisher||Association for Computing Machinery, Inc|
|Number of pages||13|
|State||Published - Jul 3 2020|
|Event||2020 ACM Conference on Designing Interactive Systems, DIS 2020 - Eindhoven, Netherlands|
Duration: Jul 6 2020 → Jul 10 2020
|Name||DIS 2020 - Proceedings of the 2020 ACM Designing Interactive Systems Conference|
|Conference||2020 ACM Conference on Designing Interactive Systems, DIS 2020|
|Period||7/6/20 → 7/10/20|
Bibliographical noteFunding Information:
This work was supported by the National Science Foundation (NSF) under Award No. IIS-2001851 and No. IIS-2000782, the NSF Program on Fairness in AI in collaboration with Amazon under Award No. IIS-1939606, and the JP Morgan Faculty Award.
© 2020 ACM.
- Algorithmic fairness
- Algorithmic trade-offs
- Case study
- Criminal prediction
- Experimental design
- Interactive visualization
- Interview study