{
  "slug": "smart-replacement-prediction-random-splits",
  "title": "A 2016 SMART predictor reached 98% recall on one Seagate model but 81% on a Hitachi model, scored with random splits on Backblaze data",
  "kind": "dataset",
  "summary": "Botezatu et al., KDD 2016, predicted disk replacement from SMART data of 50,984 Backblaze disks: 98% recall on one Seagate model and 81% on one Hitachi model, scored with 100 random 80/20 splits. Cross-check rows come from Azure (ATC 2018), Backblaze (2016), and a data center operator (FAST 2020).",
  "license": "Small derived table of figures printed in Botezatu et al. (KDD 2016), Xu et al. (ATC 2018), a Backblaze post of 6 October 2016, and Lu et al. (FAST 2020), with credit. Not a Creative Commons license. The papers remain with their authors or publishers. This file is not a copy of the papers and not the data.",
  "licenseUrl": "https://kdd.org/kdd2016/papers/files/adf0849-botezatuA.pdf",
  "sourceUrl": "https://kdd.org/kdd2016/papers/files/adf0849-botezatuA.pdf",
  "accessed": "2026-10-11",
  "rowCount": 15,
  "columns": [
    {
      "name": "measure",
      "type": "string",
      "description": "The quantity as the source names it."
    },
    {
      "name": "value_low",
      "type": "number",
      "description": "Lower end of a printed range. Empty when the source prints a single value."
    },
    {
      "name": "value_high",
      "type": "number",
      "description": "Single printed value, or the upper end of a range."
    },
    {
      "name": "unit",
      "type": "string",
      "description": "Unit of the value columns: disks, months, percent, splits, or correlation coefficient."
    },
    {
      "name": "scope",
      "type": "string",
      "description": "Population and window the value applies to."
    },
    {
      "name": "note",
      "type": "string",
      "description": "What the value is not, or the source wording behind it."
    },
    {
      "name": "citation_id",
      "type": "string",
      "description": "Id of the opened source in the citations list."
    }
  ],
  "downloadPath": "/data/datasets/smart-replacement-prediction-random-splits.csv",
  "humanPage": "https://hesela.com/analyses/smart-replacement-prediction-random-splits/",
  "limits": [
    "Two disk families from one public fleet, 2013 to 2015; a model is needed per manufacturer.",
    "Scores come from random 80/20 splits of a downsampled set, not from a split by time.",
    "The paper does not say the test set keeps the true 2.5% to 3% share of replaced disks.",
    "The Backblaze post is the same fleet's own analysis, not an independent dataset.",
    "The cross-check rows use other data and other definitions."
  ],
  "citations": [
    {
      "id": "botezatu-kdd16-pdf",
      "title": "Predicting Disk Replacement towards Reliable Data Centers, Botezatu, Giurgiu, Bogojeska, and Wiesmann, ACM SIGKDD 2016, pages 39 to 48 (KDD PDF)",
      "url": "https://kdd.org/kdd2016/papers/files/adf0849-botezatuA.pdf",
      "accessed": "2026-10-11"
    },
    {
      "id": "xu-atc18-pdf",
      "title": "Improving Service Availability of Cloud Systems by Predicting Disk Error, Xu et al., USENIX ATC 2018 (USENIX PDF, section 3 on online prediction)",
      "url": "https://www.usenix.org/system/files/conference/atc18/atc18-xu-yong.pdf",
      "accessed": "2026-10-11"
    },
    {
      "id": "backblaze-smart-2016",
      "title": "What SMART Stats Tell Us About Hard Drives, Backblaze, 6 October 2016",
      "url": "https://www.backblaze.com/blog/what-smart-stats-indicate-hard-drive-failures/",
      "accessed": "2026-10-11"
    },
    {
      "id": "lu-fast20-pdf",
      "title": "Making Disk Failure Predictions SMARTer!, Lu et al., USENIX FAST 2020 (USENIX PDF, section 4)",
      "url": "https://www.usenix.org/system/files/fast20-lu.pdf",
      "accessed": "2026-10-11"
    }
  ]
}