Dataset Open Access

Synthetic Dataset for Outlier Detection

Koncar, Philipp


Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.1171077", 
  "title": "Synthetic Dataset for Outlier Detection", 
  "issued": {
    "date-parts": [
      [
        2018, 
        2, 
        11
      ]
    ]
  }, 
  "abstract": "<p>This synthetically generated dataset can be used to evaluate outlier detection algorithms. It has 10 attributes and 1000 observations, of which 100 are&nbsp;labeled as outliers. Two-dimensional combinations of attributes form differently shaped clusters.</p>\n\n<ul>\n\t<li>Attribute 0 &amp; Attribute&nbsp;1: Two circular clusters</li>\n\t<li>Attribute&nbsp;2 &amp; Attribute&nbsp;3: Two banana shaped clusters</li>\n\t<li>Attribute&nbsp;4 &amp; Attribute&nbsp;5: Three point clouds</li>\n\t<li>Attribute&nbsp;6 &amp; Attribute&nbsp;7: Two point clouds with variances</li>\n\t<li>Attribute&nbsp;8 &amp; Attribute&nbsp;9: Three anisotropic shaped clusters.&nbsp;</li>\n</ul>\n\n<p>The &quot;outlier&quot; column states whether an observation is an outlier or not. Additionally, the .zip file contains 10 stratified randomized train test splits (70% train, 30% test).</p>", 
  "author": [
    {
      "family": "Koncar, Philipp"
    }
  ], 
  "version": "1.0", 
  "type": "dataset", 
  "id": "1171077"
}
1,319
134
views
downloads
All versions This version
Views 1,3191,321
Downloads 134134
Data volume 135.4 MB135.4 MB
Unique views 1,2691,271
Unique downloads 129129

Share

Cite as