Overcoming Algorithm Aversion with Transparency: Can Transparent Predictions Change User Behavior?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bohlen, Lasse, Kruschel, Sven, Rosenberger, Julian, Zschech, Patrick, Kraus, Mathias
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915428192747520
author Bohlen, Lasse
Kruschel, Sven
Rosenberger, Julian
Zschech, Patrick
Kraus, Mathias
author_facet Bohlen, Lasse
Kruschel, Sven
Rosenberger, Julian
Zschech, Patrick
Kraus, Mathias
contents Previous work has shown that allowing users to adjust a machine learning (ML) model's predictions can reduce aversion to imperfect algorithmic decisions. However, these results were obtained in situations where users had no information about the model's reasoning. Thus, it remains unclear whether interpretable ML models could further reduce algorithm aversion or even render adjustability obsolete. In this paper, we conceptually replicate a well-known study that examines the effect of adjustable predictions on algorithm aversion and extend it by introducing an interpretable ML model that visually reveals its decision logic. Through a pre-registered user study with 280 participants, we investigate how transparency interacts with adjustability in reducing aversion to algorithmic decision-making. Our results replicate the adjustability effect, showing that allowing users to modify algorithmic predictions mitigates aversion. Transparency's impact appears smaller than expected and was not significant for our sample. Furthermore, the effects of transparency and adjustability appear to be more independent than expected.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03168
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Overcoming Algorithm Aversion with Transparency: Can Transparent Predictions Change User Behavior?
Bohlen, Lasse
Kruschel, Sven
Rosenberger, Julian
Zschech, Patrick
Kraus, Mathias
Machine Learning
Previous work has shown that allowing users to adjust a machine learning (ML) model's predictions can reduce aversion to imperfect algorithmic decisions. However, these results were obtained in situations where users had no information about the model's reasoning. Thus, it remains unclear whether interpretable ML models could further reduce algorithm aversion or even render adjustability obsolete. In this paper, we conceptually replicate a well-known study that examines the effect of adjustable predictions on algorithm aversion and extend it by introducing an interpretable ML model that visually reveals its decision logic. Through a pre-registered user study with 280 participants, we investigate how transparency interacts with adjustability in reducing aversion to algorithmic decision-making. Our results replicate the adjustability effect, showing that allowing users to modify algorithmic predictions mitigates aversion. Transparency's impact appears smaller than expected and was not significant for our sample. Furthermore, the effects of transparency and adjustability appear to be more independent than expected.
title Overcoming Algorithm Aversion with Transparency: Can Transparent Predictions Change User Behavior?
topic Machine Learning
url https://arxiv.org/abs/2508.03168