{
  "fetched_at": "2026-10-19T20:26:40Z",
  "source_url": "https://www.kaggle.com/competitions/companies-bankruptcy-forecast/data",
  "pages": [
    {
      "name": "rules",
      "content": "\n\t<!-- Begin Base Rules -->\n    <h3>One account per participant</h3>\n    <p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\n    <h3>No private sharing outside teams</h3>\n    <p>\n        Privately sharing code or data outside of teams is not permitted.\n        It's okay to share code if made available to all participants on the forums.\n    </p>\n    <h3>Team Mergers</h3>\n    <p>Team mergers are not allowed in this competition.</p>\n\n    <h3>Team Limits</h3>\n    <p>There is no maximum team size.</p>\n    <h3>Submission Limits</h3>\n    <p>You may submit a maximum of 5 entries per day.</p>\n    <p>You may select up to 1 final submission for judging.</p>\n    <h3>Competition Timeline</h3>\n    <p>Start Date: <strong>11/2/2018 12:00 AM UTC</strong></p>\n    <p>Merger Deadline: <strong>None</strong></p>\n    <p>Entry Deadline: <strong>None</strong></p>\n    <p>End Date: <strong>11/28/2018 12:00 AM UTC</strong></p>\n\t<!-- End Base Rules -->\n<p>The rules page is a bit special: it will auto-update the text based on the parameters of the competition. The rules you need to add here are any additional rules relating to dataset usage. You may also put grading information here.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<p>The dataset is about bankruptcy prediction of Polish companies. The data was collected from Emerging Markets Information Service (EMIS), which is a database containing information on emerging markets around the world. The bankrupt companies were analyzed in the period 2000-2012, while the still operating companies were evaluated from 2007 to 2013. </p>\n<h2>File descriptions</h2>\n<ul>\n<li><strong>bankruptcy_Train.csv</strong> - the training set with both predictors and response variable</li>\n<li><strong>bankruptcy_Test_X.csv</strong> - the test set with ID and predictors</li>\n</ul>\n<h2>Data fields</h2>\n<ul>\n<li><strong>attr1</strong> -\tnet profit / total assets </li>\n<li><strong>attr2</strong> -\ttotal liabilities / total assets </li>\n<li><strong>attr3</strong> -\tworking capital / total assets </li>\n<li><strong>attr4</strong> -\tcurrent assets / short-term liabilities </li>\n<li><strong>attr5</strong> -\t[(cash + short-term securities + receivables - short-term liabilities) / (operating expenses - depreciation)] * 365 </li>\n<li><strong>attr6</strong> -\tretained earnings / total assets </li>\n<li><strong>attr7</strong> -\tEBIT / total assets </li>\n<li><strong>attr8</strong> -\tbook value of equity / total liabilities </li>\n<li><strong>attr9</strong> -\tsales / total assets </li>\n<li><strong>attr10</strong> -\tequity / total assets </li>\n<li><strong>attr11</strong> -\t(gross profit + extraordinary items + financial expenses) / total assets </li>\n<li><strong>attr12</strong> -\tgross profit / short-term liabilities </li>\n<li><strong>attr13</strong> -\t(gross profit + depreciation) / sales </li>\n<li><strong>attr14</strong> -\t(gross profit + interest) / total assets </li>\n<li><strong>attr15</strong> -\t(total liabilities * 365) / (gross profit + depreciation) </li>\n<li><strong>attr16</strong> -\t(gross profit + depreciation) / total liabilities </li>\n<li><strong>attr17</strong> -\ttotal assets / total liabilities </li>\n<li><strong>attr18</strong> -\tgross profit / total assets </li>\n<li><strong>attr19</strong> -\tgross profit / sales </li>\n<li><strong>attr20</strong> -\t(inventory * 365) / sales </li>\n<li><strong>attr21</strong> -\tsales (n) / sales (n-1) </li>\n<li><strong>attr22</strong> -\tprofit on operating activities / total assets </li>\n<li><strong>attr23</strong> -\tnet profit / sales </li>\n<li><strong>attr24</strong> -\tgross profit (in 3 years) / total assets </li>\n<li><strong>attr25</strong> -\t(equity - share capital) / total assets </li>\n<li><strong>attr26</strong> -\t(net profit + depreciation) / total liabilities </li>\n<li><strong>attr27</strong> -\tprofit on operating activities / financial expenses </li>\n<li><strong>attr28</strong> -\tworking capital / fixed assets </li>\n<li><strong>attr29</strong> -\tlogarithm of total assets </li>\n<li><strong>attr30</strong> -\t(total liabilities - cash) / sales </li>\n<li><strong>attr31</strong> -\t(gross profit + interest) / sales </li>\n<li><strong>attr32</strong> -\t(current liabilities * 365) / cost of products sold </li>\n<li><strong>attr33</strong> -\toperating expenses / short-term liabilities </li>\n<li><strong>attr34</strong> -\toperating expenses / total liabilities </li>\n<li><strong>attr35</strong> -\tprofit on sales / total assets </li>\n<li><strong>attr36</strong> -\ttotal sales / total assets </li>\n<li><strong>attr37</strong> -\t(current assets - inventories) / long-term liabilities </li>\n<li><strong>attr38</strong> -\tconstant capital / total assets </li>\n<li><strong>attr39</strong> -\tprofit on sales / sales </li>\n<li><strong>attr40</strong> -\t(current assets - inventory - receivables) / short-term liabilities </li>\n<li><strong>attr41</strong> -\ttotal liabilities / ((profit on operating activities + depreciation) * (12/365)) </li>\n<li><strong>attr42</strong> -\tprofit on operating activities / sales </li>\n<li><strong>attr43</strong> -\trotation receivables + inventory turnover in days </li>\n<li><strong>attr44</strong> -\t(receivables * 365) / sales </li>\n<li><strong>attr45</strong> -\tnet profit / inventory </li>\n<li><strong>attr46</strong> -\t(current assets - inventory) / short-term liabilities </li>\n<li><strong>attr47</strong> -\t(inventory * 365) / cost of products sold </li>\n<li><strong>attr48</strong> -\tEBITDA (profit on operating activities - depreciation) / total assets </li>\n<li><strong>attr49</strong> -\tEBITDA (profit on operating activities - depreciation) / sales </li>\n<li><strong>attr50</strong> -\tcurrent assets / total liabilities </li>\n<li><strong>attr51</strong> -\tshort-term liabilities / total assets </li>\n<li><strong>attr52</strong> -\t(short-term liabilities * 365) / cost of products sold) </li>\n<li><strong>attr53</strong> -\tequity / fixed assets </li>\n<li><strong>attr54</strong> -\tconstant capital / fixed assets </li>\n<li><strong>attr55</strong> -\tworking capital </li>\n<li><strong>attr56</strong> -\t(sales - cost of products sold) / sales </li>\n<li><strong>attr57</strong> -\t(current assets - inventory - short-term liabilities) / (sales - gross profit - depreciation) </li>\n<li><strong>attr58</strong> -\ttotal costs /total sales </li>\n<li><strong>attr59</strong> -\tlong-term liabilities / equity </li>\n<li><strong>attr60</strong> -\tsales / inventory </li>\n<li><strong>attr61</strong> -\tsales / receivables </li>\n<li><strong>attr62</strong> -\t(short-term liabilities *365) / sales </li>\n<li><strong>attr63</strong> -\tsales / short-term liabilities </li>\n<li><strong>attr64</strong> -\tsales / fixed assets</li>\n<li><strong>class</strong> -\tthe response variable Y: 0 = did not bankrupt; 1 = bankrupt </li>\n\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>Bankruptcy prediction has been a subject of interests for almost a century\nand it still ranks high among hottest topics in economics. The aim of predicting\nfinancial distress is to develop a predictive model that combines various\neconometric measures and allows to foresee a financial condition of a firm.</p>\n<p>The purpose of the bankruptcy prediction is to assess the financial condition\nof a company and its future perspectives within the context of longterm\noperation on the market (Zieba, et al., 2016).</p>\n<h2>Acknowledgements</h2>\n<p>We thank Sebastian Tomczak for providing this dataset. The training and testing data are processed based on the Polish companies bankruptcy data Data Set available at UCI Machine Learning Repository. Data has been preprocessed by removing missing values and standardizing columns. The training and testing data are randomly selected from the whole data sets. Reference: Zieba, Maciej and Tomczak, Sebastian K and Tomczak, Jakub M (2016), Ensemble Boosted Trees with Synthetic Features Generation in Application to Bankruptcy Prediction, Expert Systems with Applications.  </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/Receiver_operating_characteristic\"> AUC, i.e., area under the receiver operator curve.</a></p>\n\n<p>In R (using the \"pROC\" package):</p>\n<p>roc_obj = roc(true_labels, predicted_probabilities)</p>\n<p>auc(roc_obj)</p>\n\n\n\n<h2>Submission Format</h2>\n<p><strong>Submission files should contain the predicted probability of bankruptcy for each test sample.</p>\n<p>The file should contain a header and have the following format:</p>\n<pre>ID, class<br />1, 0.01<br /><span style=\"font-size: 14px; line-height: 1.4em;\">2, 0.20<br />3, 0.99<br /></span><span style=\"font-size: 14px; line-height: 1.4em;\">4, 0.40<br /></span><span style=\"font-size: 14px; line-height: 1.4em;\">etc.</span></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}