Presentation
Exploring the Effects of Machine Learning Models of Varying Transparency on Performance Outcomes
DescriptionMachine learning models are becoming increasingly used in a variety of settings but are often black box in nature. Recent work has emphasized the need for models to be more interpretable to end users, and calibrated classification models (CCMs) are one such type of model. CCMs provide more accurate confidence intervals to the end user, however little research has investigated how CCM confidence estimates and actual classification accuracy impact user performance. Therefore, the current study investigated how expectations for machine learning models and their actual behaviors influenced task performance and decision time. Results demonstrated that models with high confidence and low classification accuracy led to the lowest performance and highest decision time in an image classification task. Limitations of the current study are discussed along with future research opportunities.
Contributor
Industrial Organizational Psychologist
Event Type
Lecture
TimeWednesday, September 11th11:15am - 11:35am MST
LocationFlagstaff
Human AI Robot Teaming (AI)