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.

arXiv commentIUI 2020

References in corpus (5)

• Questioning the AI: Informing Design Practices for Explainable AI User Experiences
• Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making
• Human-AI Collaboration in Data Science: Exploring Data Scientists' Perceptions of Automated AI
• Trust in Data Science: Collaboration, Translation, and Accountability in Corporate Data Science Projects
• ATMSeer: Increasing Transparency and Controllability in Automated Machine Learning

Cited by in corpus (15)

• "Brilliant AI Doctor" in Rural China: Tensions and Challenges in AI-Powered CDSS Deployment
• Documentation Matters: Human-Centered AI System to Assist Data Science Code Documentation in Computational Notebooks
• Investigating and Designing for Trust in AI-powered Code Generation Tools
• AutoDS: Towards Human-Centered Automation of Data Science
• Better Together? An Evaluation of AI-Supported Code Translation
• Telling Stories from Computational Notebooks: AI-Assisted Presentation Slides Creation for Presenting Data Science Work
• 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
• AutoML in The Wild: Obstacles, Workarounds, and Expectations
• Model LineUpper: Supporting Interactive Model Comparison at Multiple Levels for AutoML
• Why is AI not a Panacea for Data Workers? An Interview Study on Human-AI Collaboration in Data Storytelling
• Identifying Explanation Needs of End-users: Applying and Extending the XAI Question Bank
• From Hazard Identification to Controller Design: Proactive and LLM-Supported Safety Engineering for ML-Powered Systems
• Towards Feature Engineering with Human and AI's Knowledge: Understanding Data Science Practitioners' Perceptions in Human&AI-Assisted Feature Engineering Design
• Practitioner Motives to Use Different Hyperparameter Optimization Methods