An explosion in Automated Machine Learning (AutoML) tools has led to numerous back-end frameworks enabling data science experts to perform Machine Learning (ML) tasks with great speed and efficiency. However, to ensure ML tools are openly accessible to all who stand to benefit from their predictive and analytical powers, we must examine how true novices and subject matter experts without ML knowledge interact with AutoML tools, perceive ML, and form their mental models of ML processes. We achieve this goal by developing a user-facing framework that combines the understandability of conversation with Large Language Models with interface scaffolding necessary to support true machine learning novices in building their own models. We then evaluate the effectiveness of our framework in a user-study with 16 novice users. Results show that our true ML novice participants felt confident performing ML tasks independently, citing the tool’s ease of use and its ability to help them formalize their ML goals.

Documentation

Starkova, Valeria (2025). CoAutoML: User Interface Framework for Machine Learning Novices using LLM-based AutoML and Test-Driven Machine Teaching, Williams College Computer Science Honors Thesis.