{
  "id": "2001.08677",
  "version": "v1",
  "published": "2020-01-23T17:19:29.000Z",
  "updated": "2020-01-23T17:19:29.000Z",
  "title": "Towards Automatic Clustering Analysis using Traces of Information Gain: The InfoGuide Method",
  "authors": [
    "Paulo Rocha",
    "Diego Pinheiro",
    "Martin Cadeiras",
    "Carmelo Bastos-Filho"
  ],
  "comment": "The 33rd International FLAIRS Conference",
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "Clustering analysis has become a ubiquitous information retrieval tool in a wide range of domains, but a more automatic framework is still lacking. Though internal metrics are the key players towards a successful retrieval of clusters, their effectiveness on real-world datasets remains not fully understood, mainly because of their unrealistic assumptions underlying datasets. We hypothesized that capturing {\\it traces of information gain} between increasingly complex clustering retrievals---{\\it InfoGuide}---enables an automatic clustering analysis with improved clustering retrievals. We validated the {\\it InfoGuide} hypothesis by capturing the traces of information gain using the Kolmogorov-Smirnov statistic and comparing the clusters retrieved by {\\it InfoGuide} against those retrieved by other commonly used internal metrics in artificially-generated, benchmarks, and real-world datasets. Our results suggested that {\\it InfoGuide} can enable a more automatic clustering analysis and may be more suitable for retrieving clusters in real-world datasets displaying nontrivial statistical properties.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-01-23T17:19:29.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "automatic clustering analysis",
      "information gain",
      "infoguide method",
      "real-world datasets",
      "displaying nontrivial statistical properties"
    ],
    "tags": [
      "conference paper"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}