{
  "fetched_at": "2026-10-20T03:55:12Z",
  "source_url": "https://www.kaggle.com/competitions/anomaly-detection/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<h2>Column Description</h2>\n<p>The description of the column are as follows:</p>\n<p>timestamp [ float ] : is provided as a Unix epoch in seconds.</p>\n<p>value [ int ] : is a real value measurement of some metric at the timestamp.</p>\n<p>is_anomaly [ boolean ] : is a boolean value which is True if the corresponding value is\nidentified as an anomaly. </p>\n<p>predicted [ float ] : is a real value prediction coming from a black box forecasting\nmodel for that timestamp. This black box forecasting model is assumed to be aware of\nonly the true data distribution.</p>\n\n<h2>Submission Format</h2>\n<p> The CSV format should contain two column, timestamp, is_anomaly score</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>Let us assume that, we have a company called \"Splash\", and you are a newly joined Machine Learning Engineer at our company, held at 30 LPA CTC. So, the below thing describes our company and the task in hand.</p>\n\n<p>Currently we at Splash, help retailers with pricing intelligence and business monitoring.</p>\n\n<p>One of our main challenges comprise of monitoring and analyzing our client's business metrics in real time for instant detection of the incidents that may impact their revenue.</p>\n\n<p>One subpart of this challenge is Anomaly Detection which generates alerts on our client's business metrics.</p>\n\n<p>The Problem Statement presented below highlights the problem which we are tackling right now</p>\n\n<h2>Column Description</h2>\n<p>The description of the column are as follows:</p>\n<p>timestamp [ float ] : is provided as a Unix epoch in seconds.</p>\n<p>value [ int ] : is a real value measurement of some metric at the timestamp.</p>\n<p>is_anomaly [ boolean ] : is a boolean value which is True if the corresponding value is\nidentified as an anomaly. </p>\n<p>predicted [ float ] : is a real value prediction coming from a black box forecasting\nmodel for that timestamp. This black box forecasting model is assumed to be aware of\nonly the true data distribution.</p>\n\n<h2>Submission Format</h2>\n<p> The CSV format should contain two column, timestamp, is_anomaly score</p>\n\n<h2>Scoring Criteria</h2>\n<p>The scoring will be determined with the help of the Mean-F-Score, because the prediction of the anomaly is the important part, merely just making all the values to be False, would result in maybe 95% accuracy, which is not the desired thing for the client, because he is concerned more about the anomaly rather than the non anomaly data.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!\n - You are free to try out all the permutations and combinations for the prediction.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}