{
  "fetched_at": "2026-10-19T11:22:27Z",
  "source_url": "https://www.kaggle.com/competitions/business-analytics-project-regression/data",
  "pages": [
    {
      "name": "data-description",
      "content": "### Data Overview\n\nThe data was stored in four separate folders: action, courier, distance, order. Each folder contains a dataframe, labeled by date. Here's some brief overview of some of the attributes, the rest can be explored on your own.\n\n#### Action\n\nThe ActionStep attribute records the delivery-man's action, you may group by wave based on courier_id and wave_index. the expect_time is the timestamp when the action was completed, and can be sorted to give the courier's sequence of actions. 'courier_wave_start_lng' and 'courier_wave_start_lat' records the geographic locations. \n\n#### Distance\n\n'source_type' and 'target_type' are categorical values containing three values: 'Assign', 'PickFood', and 'DeliverFood'. When type is 'Assign', the location attributes represent the courier's location; When type is 'PickFood' the location attributes represent the vendor's location; When type is 'DeliverFood' the location attributes represent the customer's location.\n\n#### Order\n\n| attribute     | explanation                      |\n\n| ------------- | -------------------------------- |\n\n| create_time   | The time the order was created   |\n\n| confirm_time  | The time the order was confirmed |\n\n| assigned_time | The time the order was assigned  |\n\n| aoi_id        | Unique ID indicating an area     |\n\n| shop_id       | Unique ID indicating a vendor    |\n\n### Prediction\n\nFor each 'action', group by courier and wave, and check 'expect_time' attribute. The non-zero values are the actual timestamps of completed actions. Your job is to predict the timestamps of zero values in this column. Ideally, after you've predicted all timestamps, ordering by the timestamps gives you the chronological order of the actions.\n\nThe available data is from 2.1 to 2.28, and we want you to predict for 2.29",
      "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.  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 item in the dataset</strong>, submission files should contain one column called ID, with a sequence from 0 to 22393. and a column of predicted expected time. The file should have a header, \"ID\" and \"expect_time\" for the two columns, and the file should have 22395 rows in total. The submission should be in CSV format</p>\n",
      "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
    }
  ]
}