An Interactive Tool for Feature Analysis of Outliers in Multi-Dimensional Data
This paper presents an interactive visualization tool for the analy-
sis of outliers in multi-dimensional data. Each data sample consists
of multiple variables (features). For a given outlier data sample,
our tool helps the user to identify which variable of the data sam-
ple makes it an outlier. Our tool consists of a scatter plot view and
variable relation graph view. The user first identifies an outlier data
sample in a scatter plot. The user selects the outlier data sample,
and the system updates the variable relation graph to visualize rela-
tionship between the variables of the outlier data sample. The user
then examines the variable relation graph and the scatter plot based
on the visualization to identify outlying variables.
- Kentaro Asai, Tsukasa Fukusato, Takeo Igarashi. An Interactive Tool for Feature Analysis of Outliers in Multi-Dimensional Data. IEEE VIS 2018. Berlin, Germany.