{
  "id": "2311.15887",
  "version": "v1",
  "published": "2023-11-27T14:55:16.000Z",
  "updated": "2023-11-27T14:55:16.000Z",
  "title": "FLASC: A Flare-Sensitive Clustering Algorithm: Extending HDBSCAN* for Detecting Branches in Clusters",
  "authors": [
    "D. M. Bot",
    "J. Peeters",
    "J. Liesenborgs",
    "J. Aerts"
  ],
  "comment": "20 pages, 11 figures, submitted to ACM TKDD",
  "categories": [
    "cs.LG",
    "cs.DB"
  ],
  "abstract": "We present FLASC, an algorithm for flare-sensitive clustering. Our algorithm builds upon HDBSCAN* -- which provides high-quality density-based clustering performance -- through a post-processing step that differentiates branches within the detected clusters' manifold, adding a type of pattern that can be discovered. Two variants of the algorithm are presented, which trade computational cost for noise robustness. We show that both variants scale similarly to HDBSCAN* in terms of computational cost and provide stable outputs using synthetic data sets, resulting in an efficient flare-sensitive clustering algorithm. In addition, we demonstrate the algorithm's benefit in data exploration over HDBSCAN* clustering on two real-world data sets.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-11-27T14:55:16.000Z"
    }
  ],
  "analyses": {
    "subjects": [
      "I.5.3",
      "H.3.3"
    ],
    "keywords": [
      "detecting branches",
      "synthetic data sets",
      "real-world data sets",
      "trade computational cost",
      "high-quality density-based clustering performance"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 20,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}