{
  "fetched_at": "2026-10-20T05:13:17Z",
  "source_url": "https://www.kaggle.com/competitions/PredictiveMaintenance/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>This page shows up underneath the data files. Here you describe what files you have provided and the format of each. There is no single format for this page that is appropriate for all competitons, but you should strive to describe as much as you can here. A little time spent describing the data here can save a lot of time answering questions later.</p>\r\n<p>Participants should be able to answer questions like these after reading the data description: What files do I need? What should I expect the data format to be? What am I predicting? What acroynms will I encounter?</p>\r\n<h2>File descriptions</h2>\r\n<ul>\r\n<li><strong>train.csv</strong> - the training set</li>\r\n<li><strong>test.csv</strong> - the test set</li>\r\n<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format</li>\r\n<li><strong>metaData.csv</strong> - supplemental information about the data</li>\r\n<li>etc...</li>\r\n</ul>\r\n<h2>Data fields</h2>\r\n<ul>\r\n<li><strong>customer_id</strong> - an anonymous id unique to a given customer</li>\r\n<li><strong>movie_id</strong> - the id of a movie</li>\r\n<li><strong>movie_title</strong> - the title of a movie</li>\r\n<li>etc...</li>\r\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is <a href=\"https://www.explorium.ai/wiki/auc/\"> Area Under the Curve </a>. The AUC score, is a performance measurement for classification problems. It tells how much the model is capable of distinguishing between classes. The higher the AUC, the better the model is in distinguishing between classes.\n\n</p><h2>Submission Format</h2>\n\n<p><strong>For every UDI in the dataset</strong>, submission files should contain two columns: UDI and Machine failure. Machine failure should be a boolean(1 or 0). \n\n</p><p>The file should contain a header and have the following format:</p>\n<pre>UDI , Machine failure\n<br>24, 0<br>\n<br>25, 0<br>\n<br>26, 1<br>\n</pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "- Don't cheat!\n- Apply yourself!\n- Have fun!\n- Good luck",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "**Attribute Information:**\nThe dataset consists of 10 000 data points stored as rows with 14 features in columns\nUID: unique identifier ranging from 1 to 10000\nproduct ID: consisting of a letter L, M, or H for low (50% of all products), medium (30%) and high (20%) as product quality variants and a variant-specific serial number\nair temperature [K]: generated using a random walk process later normalized to a standard deviation of 2 K around 300 K\nprocess temperature [K]: generated using a random walk process normalized to a standard deviation of 1 K, added to the air temperature plus 10 K.\nrotational speed [rpm]: calculated from a power of 2860 W, overlaid with a normally distributed noise\ntorque [Nm]: torque values are normally distributed around 40 Nm with a σ = 10 Nm and no negative values.\ntool wear [min]: The quality variants H/M/L add 5/3/2 minutes of tool wear to the used tool in the process. and a\n'machine failure' label that indicates, whether the machine has failed in this particular datapoint for any of the following failure modes are true.\n\nThe machine failure consists of five independent failure modes\ntool wear failure (TWF): the tool will be replaced of fail at a randomly selected tool wear time between 200 – 240 mins (120 times in our dataset). At this point in time, the tool is replaced 69 times, and fails 51 times (randomly assigned).\nheat dissipation failure (HDF): heat dissipation causes a process failure, if the difference between air- and process temperature is below 8.6 K and the tool’s rotational speed is below 1380 rpm. This is the case for 115 data points.\npower failure (PWF): the product of torque and rotational speed (in rad/s) equals the power required for the process. If this power is below 3500 W or above 9000 W, the process fails, which is the case 95 times in our dataset.\noverstrain failure (OSF): if the product of tool wear and torque exceeds 11,000 minNm for the L product variant (12,000 M, 13,000 H), the process fails due to overstrain. This is true for 98 datapoints.\nrandom failures (RNF): each process has a chance of 0,1 % to fail regardless of its process parameters. This is the case for only 5 datapoints, less than could be expected for 10,000 datapoints in our dataset.\n\nIf at least one of the above failure modes is true, the process fails and the 'machine failure' label is set to 1. It is therefore not transparent to the machine learning method, which of the failure modes has caused the process to fail ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}