AutoDS: Towards Human-Centered Automation of Data Science
This work addresses the problem of automating data science workflows for data scientists and domain experts, though it is incremental as it builds on existing AutoML techniques.
The paper tackles the laborious tasks in data science projects by introducing AutoDS, an AutoML system that automates ML configurations, preprocessing, algorithm selection, and model training, resulting in improved productivity, higher model quality, and fewer errors, but lower human confidence scores, as shown in a study with 30 professional data scientists.
Data science (DS) projects often follow a lifecycle that consists of laborious tasks for data scientists and domain experts (e.g., data exploration, model training, etc.). Only till recently, machine learning(ML) researchers have developed promising automation techniques to aid data workers in these tasks. This paper introduces AutoDS, an automated machine learning (AutoML) system that aims to leverage the latest ML automation techniques to support data science projects. Data workers only need to upload their dataset, then the system can automatically suggest ML configurations, preprocess data, select algorithm, and train the model. These suggestions are presented to the user via a web-based graphical user interface and a notebook-based programming user interface. We studied AutoDS with 30 professional data scientists, where one group used AutoDS, and the other did not, to complete a data science project. As expected, AutoDS improves productivity; Yet surprisingly, we find that the models produced by the AutoDS group have higher quality and less errors, but lower human confidence scores. We reflect on the findings by presenting design implications for incorporating automation techniques into human work in the data science lifecycle.