How far are we with automated machine learning? characterization and challenges of AutoML toolkits

• Published in: Empirical software engineering : an international journal Vol. 29; no. 4; p. 91
• Main Authors: Al Alamin, Md Abdullah, Uddin, Gias
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.07.2024; Springer Nature B.V
• Subjects: Algorithms; Automation; Cloud computing; Collaboration; Compilers; Computer Science; Dirichlet problem; Empirical analysis; Interpreters; Machine learning; Machine Learning Techniques for Software Quality Evaluation (MaLTeSQuE); Programming Languages; Questions; Rapid prototyping; Software engineering; Software Engineering/Programming and Operating Systems; Subject specialists; Systems design; Toolkits; Virtual communities; AutoML; ML system engineering; Automated machine learning
• ISSN: 1382-3256; 1573-7616
• DOI: 10.1007/s10664-024-10450-y

Automated Machine Learning aka AutoML toolkits are low/no-code software that aim to democratize ML system application development by ensuring rapid prototyping of ML models and by enabling collaboration across different stakeholders in ML system design (e.g., domain experts, data scientists, etc.). It is thus important to know the state of current AutoML toolkits and the challenges ML practitioners face while using those toolkits. In this paper, we first offer a characterization of currently available AutoML toolits by analyzing 37 top AutoML tools and platforms. We find that the top AutoML platforms are mostly cloud-based. Most of the tools are optimized for the adoption of shallow ML models. Second, we present an empirical study of 14.3K AutoML related posts from Stack Overflow (SO) that we analyzed using topic modelling algorithm LDA (Latent Dirichlet Allocation) to understand the challenges of ML practitioners while using the AutoML toolkits. We find 13 topics in the AutoML related discussions in SO. The 13 topics are grouped into four categories: MLOps (43% of all questions), Model (28% questions), Data (27% questions), and Documentation (2% questions). Most questions are asked during Model training (29%) and Data preparation (25%) phases. AutoML practitioners find the MLOps topic category most challenging. Topics related to the MLOps category are the most prevalent and popular for cloud-based AutoML toolkits. Based on our study findings, we provide 15 recommendations to improve the adoption and development of AutoML toolkits.