{
  "fetched_at": "2026-10-19T21:48:54Z",
  "source_url": "https://www.kaggle.com/competitions/data-mining-feature-engineering/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Files\n\n*   **data_train.csv** - the training set\n*   **Y_train.csv** - the train target variable\n*   **data_test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n\n## Columns\n\n*   `ID` - identifier\n*   `month` - month in which the key figure was collected from the customer (1 = January, 12 = December)\n*   The data set also contains 20 categorical (X1-X20) and 20 numerical variables (X21-X40) whose meaning is unknown.\n\nThe data set was generated artificially.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "**Data**\n\n- **Train data:** `data_train.csv` (Contains the features measured over 12 months for the individual business customers. You must generate meaningful features from this. Not everything could be measured for all business customers every month. You must therefore be able to deal with any NAs).\n- **Target variable:** `Y_train.csv` (Categorical target variable, link these via the customer ID).\n- **Test data:** `data_test.csv` (For model evaluation using unseen data.)\n- The data is generated artificially, you do not have to worry about the meaning of the variables.\n\n**Requirements**\n\n- Generate useful features from the training data.\n- Handle missing data (NA values).\n- The model can be implemented in R or Python.\n- Save your forecasts in a CSV file with the columns `ID` and `Y`\n- **Example of submission:** `sample_submission.csv` (The submission contains the ID of the customer plus the probability of a recommendation (rec)).\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated on [area under the ROC curve]\n\n## Submission File\nFor each ID in the test set, you must predict a probability for the target variable rec. The file should contain a header and have the following format:\n\n    ID,Y\n    2,0.124\n    5,0.526\n    6,0.637\n    etc.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Have fun :)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "**Background**\n\nCompanies protect themselves against risks such as industrial accidents, legal disputes, cyber attacks and business interruptions through insurance. Some insurance policies are required by law, others are not. The insurance company XYZ AG has collected monthly data from its business customers over the past year and evaluated whether their insurance portfolios need to be adjusted.\n\n**Goal:** \nDevelop a model that can automate the decision to adjust insurance portfolios. The question is whether an adjustment to the portfolio is recommended.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}