Trust in AutoML: Exploring Information Needs for Establishing Trust in Automated Machine Learning Systems

TL;DR

This paper investigates the information factors that influence data scientists' trust in AutoML systems, highlighting the importance of transparency and performance metrics for trust establishment.

Contribution

It provides empirical insights into trust factors in AutoML, emphasizing transparency features and key information types that enhance user trust.

Findings

Transparency features increase trust and understanding.

Model performance metrics are crucial for trust.

Visualizations significantly impact trust decisions.

Abstract

We explore trust in a relatively new area of data science: Automated Machine Learning (AutoML). In AutoML, AI methods are used to generate and optimize machine learning models by automatically engineering features, selecting models, and optimizing hyperparameters. In this paper, we seek to understand what kinds of information influence data scientists' trust in the models produced by AutoML? We operationalize trust as a willingness to deploy a model produced using automated methods. We report results from three studies -- qualitative interviews, a controlled experiment, and a card-sorting task -- to understand the information needs of data scientists for establishing trust in AutoML systems. We find that including transparency features in an AutoML tool increased user trust and understandability in the tool; and out of all proposed features, model performance metrics and visualizations are the most important information to data scientists when establishing their trust with an AutoML tool.