{
  "fetched_at": "2026-10-19T10:46:07Z",
  "source_url": "https://www.kaggle.com/competitions/business-analytics-summer20-regression/data",
  "pages": [
    {
      "name": "data-description",
      "content": "### Data Overview\n\nThe data was already pre-processed. Here's some brief overview of some of the attributes, the rest can be explored on your own.\n\n**'courier_id', 'wave_index', 'tracking_id', 'date', 'group', 'id',:**\n\nThese are the demographic information of the order and its courier. The column names are somewhat self-explanatory.\n\n**'courier_wave_start_lng', 'courier_wave_start_lat':**\n\nThese are the starting longitude and latitude of that wave of a certain courier\n\n**'level', 'speed', 'max_load':**\n\nThese are the courier information: the level of the courier, the speed of the courier and the max load of the courier\n\n**'weather_grade':**\n\nThis is the weather condition of the order\n\n**'aoi_id':**\n\nThe id of the Area of Interest (i.e. the delivery destination)\n\n**'shop_id':**\n\nThe id of the shop\n      \n**'source_type', 'source_tracking_id', 'source_lng', 'source_lat':**\n\nThe information of the courier's previous action.\n\n**'target_lng', 'target_lat':**\n\nGeographical information of the target\n\n**'grid_distance':**\n\nThe shortest traversable distance to the target provided by the GPS\n\n**'hour':**\n\nThe hour in the day\n\n**'urgency'**\n\nIdentifies how urgent the order is\n\n**'action_type'**\n\nThe target variable in classification. This is masked from the test set\n\n**'expected_use_time':**\n\nThe target variable in regression. This is also masked from the test set\n\nNOT ALL VARIABLES ARE NECESSARILY NEEDED\n\nYou should use your own judgement as to what to use for your model.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Within the context of Eleme delivery service, at every moment the command platform of \"Smart Logistics\" sends orders from customers to delivery-men for instant delivery. The decision being made by the delivery-men are mainly two-fold: pick-up in store, and delivery to customers. At one specific moment, the delivery-man may receive orders assigned to him, while he has unfinished orders which are previously assigned. He would need to make a decision as to what to do next, based on his order status and geographical location. The goal is to build a model to predict the delivery-man's next move, based on his historical decision and current status.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<hr />\n<p>The evaluation metric for this competition is MAE-Score</a>.  The MAE score is given by:</p>\n<p>\\[ MAE = \\sum_{i=0}^{n}{\\left|predict\\_time_i - expect\\_time_i\\right|}\\]</p>\n\n<h2>Submission Format</h2>\n<p><strong>For every author in the dataset</strong>, submission files should contain all columns of the action[time].csv, without 0 timestamps.",
      "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
    }
  ]
}