{
  "fetched_at": "2026-10-19T07:59:44Z",
  "source_url": "https://www.kaggle.com/competitions/frauddetect/data",
  "pages": [
    {
      "name": "data-description",
      "content": "\n<p>The data is broken into two files identity and transaction, which are joined by TransactionID. Not all transactions have corresponding identity information.</p>\n<h2>File descriptions</h2>\n<ul>\n<li><strong>train_{transaction, identity}.csv </strong> - the training set</li>\n<li><strong>test_{transaction, identity}.csv</strong> - the test set (you must predict the isFraud value for these observations)</li>\n<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format</li>\n</ul>\n\n<h3>Transaction Table</h3>\n<ul>\n<li>TransactionDT: timedelta from a given reference datetime (not an actual timestamp)</li>\n<li>TransactionAMT: transaction payment amount in USD</li>\n<li>ProductCD: product code, the product for each transaction</li>\n<li>card1 - card6: payment card information, such as card type, card category, issue bank, country, etc.</li>\n<li>addr: address</li>\n<li>dist: distance</li>\n<li>P_ and (R__) emaildomain: purchaser and recipient email domain</li>\n<li>C1-C14: counting, such as how many addresses are found to be associated with the payment card, etc. The actual meaning is masked.</li>\n<li>D1-D15: timedelta, such as days between previous transaction, etc.</li>\n<li>M1-M9: match, such as names on card and address, etc.</li>\n<li>Vxxx: Vesta engineered rich features, including ranking, counting, and other entity relations.</li><br>\nCategorical Features:<br>\nProductCD<br>\ncard1 - card6<br>\naddr1, addr2<br>\nP_emaildomain<br>\nR_emaildomain<br>\nM1 - M9<br>\n</ul>\n<h3>Identity Table</h3>\n<p>Variables in this table are identity information – network connection information (IP, ISP, Proxy, etc) and digital signature (UA/browser/os/version, etc) associated with transactions.<br>\nThey're collected by Vesta’s fraud protection system and digital security partners.<br>\n(The field names are masked and pairwise dictionary will not be provided for privacy protection and contract agreement)</p>\n\nCategorical Features:<br>\nDeviceType<br>\nDeviceInfo<br>\nid_12 - id_38<br>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>Imagine standing at the check-out counter at the grocery store with a long line behind you and the cashier not-so-quietly announces that your card has been declined. In this moment, you probably aren’t thinking about the data science that determined your fate.</p>\n\n<p>Embarrassed, and certain you have the funds to cover everything needed for an epic nacho party for 50 of your closest friends, you try your card again. Same result. As you step aside and allow the cashier to tend to the next customer, you receive a text message from your bank. “Press 1 if you really tried to spend $500 on cheddar cheese.”</p>\n\n<p>While perhaps cumbersome (and often embarrassing) in the moment, this fraud prevention system is actually saving consumers millions of dollars per year</p>\n<p>So, In this competition  you are predicting the probability that an online transaction is fraudulent, as denoted by the binary target isFraud.</p>\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>Submissions are evaluated on area under the ROC curve between the predicted probability and the observed target.</p>\n<h3>Submission File</h3>\nFor each TransactionID in the test set, you must predict a probability for the isFraud variable. The file should contain a header and have the following format:\n<pre>&lt;p&gt;TransactionID,isFraud<br>\n3663549,0.5<br>\n3663550,0.5<br>\n3663551,0.5<br>\netc.&lt;/p&gt;</pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "<h2>One account per participant</h2>\n<p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\n<h2>No private sharing outside teams</h2>\n<p>Privately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums. </p>\n<h2>Team Mergers</h2>\n<p>Team mergers are allowed in this competition and deadline for team mergers is 23rd Sept, 2020 11:59 PM IST.</p>\n<h2>Team Limit</h2>\n<p>Maximum Team Size is 3.</p>\n<h2>General Guidelines</h2>\n<ul>\n<li>Use of any pretrained model is not allowed.</li>\n<li>Any use of deep learning approaches is not allowed. Please stick to classical approaches.</li>\n<li>No use of External Data is allowed, only the data provided with the competition has to be used.</li>\n</ul>\n<h2>Submission Limit</h2>\n<p>You may submit a maximum of 5 entries per day till 10th Oct, 2020 11:59 PM IST and 2 submissions after that.<br>\nYou may select up to 2 final submissions for judging.</p>\n<h2>Competition Deadline</h2>\n<p>End Date: 18th Dec, 2020 11:59 PM IST</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}