{
  "dataset_url": "https://archive.ics.uci.edu/dataset/352/online+retail",
  "download_url": "https://archive.ics.uci.edu/static/public/352/online+retail.zip",
  "attribution": "Chen, D. (2015). Online Retail. UCI Machine Learning Repository. DOI: 10.24432/C5BW33. CC BY 4.0.",
  "analysis_date": "2026-10-03",
  "archive_sha256": "f5385cbb54bbebf7196389109c6b0621faab0c304e3702548165e71c84aede8b",
  "xlsx_sha256": "43465a06f2ccf7c8b5bd2892bc7defb52f97487934fe93b16ae4c3936424676d",
  "source_period": [
    "2010-12-01 08:26:00",
    "2011-12-09 12:50:00"
  ],
  "reference_date": "2011-12-10",
  "currency": "GBP",
  "monetary_definition": "Sum of positive quantity times positive unit price on non-cancelled invoices with CustomerID; not net revenue or profit.",
  "duplicate_policy": "Preserve exact duplicates; no unique line ID establishes accidental duplication.",
  "counts": {
    "source_rows": 541909,
    "exact_duplicate_rows_preserved": 5268,
    "missing_customer_id": 135080,
    "cancelled_invoice": 8905,
    "nonpositive_quantity": 0,
    "nonpositive_unit_price": 40,
    "eligible_rows": 397884
  },
  "customers": 4338,
  "invoices": 18532,
  "positive_purchase_amount_gbp": 8911407.904,
  "top_20_percent_customer_count": 868,
  "top_20_percent_positive_purchase_share": 0.7461713718676614,
  "practice_recent_repeat_customers_R_le_30_F_ge_5": 787,
  "practice_lapsed_repeat_customers_R_gt_90_F_ge_5": 71,
  "practice_thresholds": "Illustrative analyst choices, not validated segment boundaries; recent and lapsed groups are disjoint but do not cover all customers.",
  "example_customers": [
    {
      "CustomerID": "12347",
      "recency_days": 3,
      "frequency": 7,
      "monetary_gbp": 4310.0,
      "last_purchase": "2011-12-07T15:52:00.000",
      "source_lines": 182
    },
    {
      "CustomerID": "12348",
      "recency_days": 76,
      "frequency": 4,
      "monetary_gbp": 1797.24,
      "last_purchase": "2011-09-25T13:13:00.000",
      "source_lines": 31
    },
    {
      "CustomerID": "12349",
      "recency_days": 19,
      "frequency": 1,
      "monetary_gbp": 1757.55,
      "last_purchase": "2011-11-21T09:51:00.000",
      "source_lines": 73
    },
    {
      "CustomerID": "12350",
      "recency_days": 311,
      "frequency": 1,
      "monetary_gbp": 334.4,
      "last_purchase": "2011-02-02T16:01:00.000",
      "source_lines": 17
    },
    {
      "CustomerID": "12352",
      "recency_days": 37,
      "frequency": 8,
      "monetary_gbp": 2506.04,
      "last_purchase": "2011-11-03T14:37:00.000",
      "source_lines": 85
    },
    {
      "CustomerID": "12353",
      "recency_days": 205,
      "frequency": 1,
      "monetary_gbp": 89.0,
      "last_purchase": "2011-05-19T17:47:00.000",
      "source_lines": 4
    }
  ],
  "sample_selection": "Six fixed IDs for hand calculation; deliberately selected, not statistically representative.",
  "sample_source_rows": 402
}