{
  "fetched_at": "2026-10-20T01:55:54Z",
  "source_url": "https://www.kaggle.com/competitions/global-hack-week-detect-credit-card-fraud/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Files\n\n*   **train.csv** - the training set\n*   **test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n\n## Columns\n\n- distance_from_home - the distance from home where the transaction happened.\n- distance_from_last_transaction - the distance from last transaction happened.\n- ratio_to_median_purchase_price - Ratio of purchased price transaction to median purchase price.\n- repeat_retailer - Is the transaction happened from same retailer.\n- used_chip - Is the transaction through chip (credit card).\n- used_pin_number - Is the transaction happened by using PIN number.\n- online_order - Is the transaction an online order.\n- fraud - Is the transaction fraudulent. This is what we're trying to predict.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Welcome to Global Hack Week: Security!!!\n\nThis time we're tackling the problem of credit card fraud: when a bad actor uses someone else's credit card information to make a purchase without their permission.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is [Mean F1-Score](https://en.wikipedia.org/wiki/F-score). The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision \\( \\text{p} \\) and recall \\( \\text{r} \\).\n\nPrecision is the ratio of true positives \\(\\text{tp}\\) to all predicted positives \\(\\text{tp} + \\text{fp}\\). Recall is the ratio of true positives \\(\\text{tp}\\) to all actual positives \\(\\text{tp} + \\text{fn}\\). The F1 score is given by:\n\n\\[ \\text{F1} = 2\\frac{\\text{p} \\cdot \\text{r}}{\\text{p}+\\text{r}}\\ \\ \\mathrm{where}\\ \\ \\text{p} = \\frac{\\text{tp}}{\\text{tp}+\\text{fp}},\\ \\ \\text{r} = \\frac{\\text{tp}}{\\text{tp}+\\text{fn}} \\]\n\nThe F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.\n\n## Submission Format\n\n**For every row in the dataset**, submission files should contain two columns: `id` and `fraud`. `DuplicateAuthorIds` should be a comma-delimited list.\n\n\nThe file should contain a header and have the following format:\n\n```\nid,fraud\n1,1\n2,0\n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "As a part of Global Hack Week, by participating in this competition you agree to abide by the [MLH Code of Conduct](https://static.mlh.io/docs/mlh-code-of-conduct.pdf).\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}