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

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.

IUI 2020

References in corpus (2)

• Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making
• Trust in Data Science: Collaboration, Translation, and Accountability in Corporate Data Science Projects

Cited by in corpus (7)

• "Brilliant AI Doctor" in Rural China: Tensions and Challenges in AI-Powered CDSS Deployment
• AutoDS: Towards Human-Centered Automation of Data Science
• Better Together? An Evaluation of AI-Supported Code Translation
• Healthcare Voice AI Assistants: Factors Influencing Trust and Intention to Use
• Humans, AI, and Context: Understanding End-Users' Trust in a Real-World Computer Vision Application
• Model LineUpper: Supporting Interactive Model Comparison at Multiple Levels for AutoML
• Identifying Explanation Needs of End-users: Applying and Extending the XAI Question Bank