{
  "fetched_at": "2026-10-20T09:42:01Z",
  "source_url": "https://www.kaggle.com/competitions/buad831spring2020/data",
  "pages": [
    {
      "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": "data-description",
      "content": "<p>You have been provided with sales data for 2 products sold in two different retail locations of the same large national grocery chain.</p>\n<h2>File descriptions</h2>\n<ul>\n<li><strong>train.csv</strong> - daily sales data (Jan 2012 - May 2013) for all stores &amp; dates in the training set</li>\n<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format (you will need to change the units from zero to do better in the competition)</li>\n</ul>\n<h2>Data fields</h2>\n<ul>\n<li><strong>date </strong>- the day of sales</li>\n<li><strong>store_nbr</strong> - an id representing one of two stores</li>\n<li><strong>items_nbr</strong> - an id representing one of two products</li>\n<li><strong>units</strong> - the quantity sold of an item on a given day</li>\n<li><strong>id</strong> - a triplet representing a store_nbr, item_nbr, and date. Form the id by concatenating these (in that order) with an underscore. E.g. \"2_1_2013-06-15\" represents store 2, item 1, sold on June 15, 2013.</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>Welcome to the University of Delaware MBA Spring 2020 forecasting competition. Daily sales data for two products sold in two stores are provided for the time period Jan 1, 2012 - May 30, 2013 (note, data is missing for Dec 25, 2012 as the stores were closed that day for the Christmas holiday). The stores are both part of a very large national retailer of grocery products. Your task is to use this historical data and any other information you deem relevant (e.g. US holidays) to forecast daily sales for the period Jun 1, 2013 - July 30, 2013.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is <a href=\"https://en.wikipedia.org/wiki/Mean_absolute_error\" target=\"_blank\">Mean Absolute Error</a>. The mean absolute error is a common measure of forecast error in time series analysis and is sometimes known as \"mean absolute deviation\". Mean absolute error (MAE) is defined as.:</p>\n<p>\\[\\frac{1}{n}\\sum_{i=1}^n \\left| y_i - \\hat{y_i}\\right| =\\frac{1}{n}\\sum_{i=1}^n \\left| e_i \\right|.\\]</p>\n<p>Where:</p>\n<ul>\n<li>The error term is \\[ |e_i| = |y_i-\\hat{y_i}| \\]</li>\n<li>Actual units sold are \\[y_i\\]</li>\n<li>Predicted units sold are \\[\\hat{y_i}\\]</li>\n<li>The number of forecasts made is \\[n\\]</li>\n</ul>\n<h2>Submission Format</h2>\n<p>Your submission file must have a header and should be structured in the following format. The id column is a triplet representing a store_nbr, item_nbr, and date. Form the id by concatenating these (in that order) with an underscore. E.g. \"2_1_2013-06-15\" represents store 2, item 1, sold on 2013-06-25. The units column is your submitted forecast. Your csv file should have one header row plus 120 forecast rows (2 stores * 2 products * 30 days = 120 forecasts).</p>\n<pre>id, units<br>1_1_2013-06-01,120<br></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}