AutoAIViz: Opening the blackbox of automated artificial intelligence with conditional parallel coordinates

Daniel Karl I. Weidele, Justin D. Weisz, Erick Oduor, Michael Muller, Josh Andres, Alexander Gray, Dakuo Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

48 Citations (Scopus)

Abstract

Artificial Intelligence (AI) can now automate the algorithm selection, feature engineering, and hyperparameter tuning steps in a machine learning workflow. Commonly known as AutoML or AutoAI, these technologies aim to relieve data scientists from the tedious manual work. However, today's AutoAI systems often present only limited to no information about the process of how they select and generate model results. Thus, users often do not understand the process, neither do they trust the outputs. In this short paper, we provide a first user evaluation by 10 data scientists of an experimental system, AutoAIViz, that aims to visualize AutoAI's model generation process. We find that the proposed system helps users to complete the data science tasks, and increases their understanding, toward the goal of increasing trust in the AutoAI system.

Original languageEnglish
Title of host publicationProceedings of the 25th International Conference on Intelligent User Interfaces, IUI 2020
PublisherAssociation for Computing Machinery (ACM)
Pages308-312
Number of pages5
ISBN (Electronic)9781450371186
DOIs
Publication statusPublished - 17 Mar 2020
Externally publishedYes
Event25th ACM International Conference on Intelligent User Interfaces, IUI 2020 - Cagliari, Italy
Duration: 17 Mar 202020 Mar 2020

Publication series

NameInternational Conference on Intelligent User Interfaces, Proceedings IUI

Conference

Conference25th ACM International Conference on Intelligent User Interfaces, IUI 2020
Country/TerritoryItaly
CityCagliari
Period17/03/2020/03/20

Fingerprint

Dive into the research topics of 'AutoAIViz: Opening the blackbox of automated artificial intelligence with conditional parallel coordinates'. Together they form a unique fingerprint.

Cite this