Publications
Publications
- 2024
Improving Human-Algorithm Collaboration: Causes and Mitigation of Over- and Under-Adherence
By: Maya Balakrishnan, Kris Ferreira and Jordan Tong
Abstract
Even if algorithms make better predictions than humans on average, humans may sometimes have private information
which an algorithm does not have access to that can improve performance. How can we help humans effectively use
and adjust recommendations made by algorithms in such situations? When deciding whether and how to override an
algorithm’s recommendations, we hypothesize that people are biased towards following a na¨ıve advice weighting (NAW)
heuristic: they take a weighted average between their own prediction and the algorithm’s, with a constant weight across
prediction instances, regardless of whether they have valuable private information. This leads to humans over-adhering
to the algorithm’s predictions when their private information is valuable and under-adhering when it is not. In an online
experiment where participants are tasked with making demand predictions for 20 products while having access to an
algorithm’s predictions, we confirm this bias towards NAW and find that it leads to a 20-61% increase in prediction error.
In a second experiment, we find that feature transparency – even when the underlying algorithm is a black box – helps
users more effectively discriminate how to deviate from algorithms, resulting in a 25% reduction in prediction error. We
make further improvements in a third experiment via an intervention designed to get users to move away from advice
weighting heuristics altogether and instead use only their private information to inform deviations, leading to a 34%
reduction in prediction error.
Keywords
Cognitive Biases; Algorithm Transparency; Forecasting and Prediction; Behavior; AI and Machine Learning; Analytics and Data Science; Cognition and Thinking
Citation
Balakrishnan, Maya, Kris Ferreira, and Jordan Tong. "Improving Human-Algorithm Collaboration: Causes and Mitigation of Over- and Under-Adherence." Working Paper, February 2024.