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.