iVLAIR - Interface Design and Prototype for Interactive Visualization-Mediated Supervised Classification
Date
2023-08-31
Authors
Kuppusami, Sanchitha
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Machine learning is widely used in various applications because of its advantages, but
not everyone can apply it effectively as it requires the use of textual programming. To
overcome this, there are several approaches that help users perform machine learning
classification without writing code. However, for most machine learning models, it
is difficult to understand how they arrive at a particular result. This challenge has
triggered a lot of research on interpretable ML methods. However, these methods also
require the user to learn how to code and implement them. In this work we introduce
iVLAIR, a web application tool that eases machine learning classification for a wider
audience and makes data more understandable to the users by transforming the data
into visualizations, thereby improving the model interpretability. We also conduct an
evaluation with machine learning experts and non-experts to compare iVLAIR with
the python approach for performing machine learning classification.
Description
Keywords
visualization, interface, ml for novices, no-code