{
  "id": "2004.09546",
  "version": "v1",
  "published": "2020-04-20T18:06:42.000Z",
  "updated": "2020-04-20T18:06:42.000Z",
  "title": "A Benchmark Study on Time Series Clustering",
  "authors": [
    "Ali Javed",
    "Byung Suk Lee",
    "Dona M. Rizzo"
  ],
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "This paper presents the first time series clustering benchmark utilizing all time series datasets currently available in the University of California Riverside (UCR) archive -- the state of the art repository of time series data. Specifically, the benchmark examines eight popular clustering methods representing three categories of clustering algorithms (partitional, hierarchical and density-based) and three types of distance measures (Euclidean, dynamic time warping, and shape-based). We lay out six restrictions with special attention to making the benchmark as unbiased as possible. A phased evaluation approach was then designed for summarizing dataset-level assessment metrics and discussing the results. The benchmark study presented can be a useful reference for the research community on its own; and the dataset-level assessment metrics reported may be used for designing evaluation frameworks to answer different research questions.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-04-20T18:06:42.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "benchmark study",
      "series clustering benchmark utilizing",
      "first time series clustering benchmark",
      "summarizing dataset-level assessment metrics",
      "time series datasets"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}