# Visus: An Interactive System for Automatic Machine Learning Model Building and Curation

## TL;DR

Visus is an interactive system that assists domain experts in building and refining machine learning pipelines generated by AutoML, addressing usability challenges and enhancing model curation through user-friendly interfaces.

## Contribution

The paper introduces Visus, a novel interactive system that supports domain experts in curating and refining AutoML-generated ML pipelines, filling a gap in usability and user engagement.

## Key findings

- Positive user feedback on system usability
- Effective support for pipeline curation and refinement
- Enhanced collaboration between domain experts and ML models

## Abstract

While the demand for machine learning (ML) applications is booming, there is a scarcity of data scientists capable of building such models. Automatic machine learning (AutoML) approaches have been proposed that help with this problem by synthesizing end-to-end ML data processing pipelines. However, these follow a best-effort approach and a user in the loop is necessary to curate and refine the derived pipelines. Since domain experts often have little or no expertise in machine learning, easy-to-use interactive interfaces that guide them throughout the model building process are necessary. In this paper, we present Visus, a system designed to support the model building process and curation of ML data processing pipelines generated by AutoML systems. We describe the framework used to ground our design choices and a usage scenario enabled by Visus. Finally, we discuss the feedback received in user testing sessions with domain experts.