{
  "fetched_at": "2026-10-19T17:04:20Z",
  "source_url": "https://www.kaggle.com/competitions/biws2020/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\n<strong>train.csv</strong> - the training set\n<p>Contains an <strong>id</strong> variable for a product, the features(variables) <strong>x_1, ..., x_100</strong> describing the products, each line/row being a single product. The class variable <strong>y</strong> contains the product class 1, 2, ..., 9. The classes and features have been anonymized to avoid advantages of background knowledge.</p>\n\n<strong>test.csv</strong> - the test set\n<p>Contains an <strong>id</strong> variable for a product, the features(variables) <strong>x_1, ..., x_100</strong> describing products, each line being a single product, similarly to the training set. Does not have the class variable <strong>y</strong>, which needs to be predicted for each product.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In this competition, you are required to classify various products sold in an online store into 9 classes depending on 100 features that describe each product. You may use any algorithm, tool, or software you like, but you may be asked to provide your code, which must be verifiable and reproducible.\n\nYour predictions for the test set will be used to award marks.\n\nThe better you score on the test set (in the final private leaderboard), the higher mark you receive.\n\nGood luck!\n\n\n<h2>Acknowledgements</h2>\n<p>We thank Vasily Tolkachev for creating the challange</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>Submissions will be evaluated using multiclass log-loss, based on the probabilities which you supply on each product class:</p>\n<p>\\[ logL = -\\dfrac{1}{N}\\sum_{i=1}^{N}\\sum_{j=1}^{K} \\textbf{1}_{y_{i} \\in j} \\log(p_{ij}) \\]</p>\n<p>where \\(N\\) is the number of observations in the test set,  \\(K\\) is the number of classes, \\(\\textbf{1}_{y_{i} \\in j}\\) is an in\ndicator function, which is 1 if a product \\(i\\) is in class \\(j\\) and 0 otherwise. \\(p_{ij}\\) is the predicted probability of a product \\(i\\) to belong to class \\(j\\) </p>\n\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
    }
  ]
}