{
  "fetched_at": "2026-10-20T09:03:04Z",
  "source_url": "https://www.kaggle.com/competitions/hackathon-2024-data-robot-oct-2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "You will have access to the following tables in AI Catalog:\nTCO Train - Primary Training File\nTCO A Process - Sensor data from process A\nTCO B Process - Sensor data from process B\nTCO test - New product ids that you will need to make predictions for\nSample Submission - What a submission file needs to look like. \n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Manufacturers can face significant costs due to product defects, which can be reduced by using a predictive model to assess product quality early in the production process.\nA predictive model would allow the manufacturer to discard or subject high-risk semi-finished products to additional processing before advancing them.\nThe dataset is from an electronics manufacturer, with bi-secondly sensor readings at the first 2 stages of a production pipeline.\nAt the end of the pipeline, a critical signal strength measurement determines if the finished product is defective.\nThe goal is to build a model to predict this critical measurement using data from the first 2 stages.\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "RMSE",
      "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",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Manufacturers can face significant costs due to product defects, which can be reduced by using a predictive model to assess product quality early in the production process.\nA predictive model would allow the manufacturer to discard or subject high-risk semi-finished products to additional processing before advancing them.\nThe dataset is from an electronics manufacturer, with bi-secondly sensor readings at the first 2 stages of a production pipeline.\nAt the end of the pipeline, a critical signal strength measurement determines if the finished product is defective.\nThe goal is to build a model to predict this critical measurement using data from the first 2 stages.\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}