{
  "fetched_at": "2026-10-19T19:00:28Z",
  "source_url": "https://www.kaggle.com/competitions/bads2021/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>The data contains real orders by customers of a clothing store. It contains 14 columns that describe the order and customer. The column names should be self-explanatory. In compliance with the shop's wishes, we are unable to answer any further questions regarding the data.<br>\n\n<p>\n<b> File descriptions</b> <br>\nBADS_WS_2021_known.csv - The training data for which the returns are known<br>\nBADS_WS_2021_unknown.csv - The final test data for which predictions are required<br>\nexample_prediction - An example of what your final prediction should look like </p>\n\n\n<p>\n<b>Data fields</b> <br>\norder_item_id - The elements for which a prediction is required<br>\nreturn - The target column: If a customer has returned the item (1) or kept it (0)<br>\n+ columns describing the order</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h2> Assignment  </h2>\n\n<p> This assignment will allow you to apply your skills in business analytics on real-world data from the field of e-commerce and customer targeting and practice the scientific methods for rigorous testing and documentation. Passing the assignment is required to participate in the exam for the class *Business Analytics and Data Science*.\nDo not use the \"Kernels\" feature to make your code public. You must not share large code chunks or complete scripts with other participants! You are required to solve the assignment individually, but we encourage discussing issues and code pieces and sharing insights both offline and on the Kaggle forum.</p>\n\n<p>For the assignment, you are highly encouraged to go beyond the standard methods taught in class, make use of the scientific literature and conduct and document your own experiments with the data. Make sure to consider all stages of a typical modeling process:\n</p>\n\n- research the relevant technical and task-related knowledge in the literature\n- gather, clean and preprocess the relevant data\n- select the best model and model parameters\n- deploy and assess the model in terms of performance and plausibility\nwith possibly revision of any step or the whole process.\n\n\n<h2> Setting </h2>\n\n<p> Customers send back a substantial part of the products that they purchase online. Return shipping is expensive for online platforms and return orders are said to reach 50% for certain industries and products. Nevertheless, free or inexpensive return shipping has become a customer expectation and de-facto standard in the fierce online competition on clothing, but shops have indirect ways to influence customer purchase behavior. For purchases where return seems likely, a shop could, for example, restrict payment options or display additional marketing communication.</p>\n\n<p>For this assignment, you are provided with real-world data by an online retailer. Your task is to identify the items that are likely to be returned. When a customer is about to purchase a item, which is likely to be returned, the shops is planning to show a warning message. Your task is to build a targeting model to balance potential sales and return risk in order to optimize shop revenue. The data you receive is artificially balanced (1:1 ratio between returns and non-returns).</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is the <b>Area-under-the-ROC-curve (AUC)</b> based on the probability scores of your model. The model will be evaluated on the<i> class</i> dataset. To pass the assignment and qualify for the exam, a final AUC score of<b> at least 0.68 </b>on the public leaderboard is required. You can submit multiple predictions and improve your score until the end date of the competition.</p>\n\n<p>For every order-item combination in the dataset, submission files should contain two and only two named columns: order_item_id and return. A higher probability score denotes a higher chance of return (1).</p>\nYou can open .csv files in a text editor (*not* Excel) to check that everything is exactly right.</p>\n\n<p>The file should contain a header and have the following format:</p>\n\norder\\_item\\_id ,return\n100001,0.4\n100002,0.05\netc.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}