{
  "fetched_at": "2026-10-19T23:00:10Z",
  "source_url": "https://www.kaggle.com/competitions/IML-L2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Files\n\n*   **train.csv** - the training set\n*   **test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n*   **metadata.txt** - supplemental information about the data",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "This problem is derived from a Portuguese bank's open dataset posted on the UCI repository. This dataset was synthetically generated by a trained GAN model on the original data, thanks to The Synthetic Data Vault Project developed at MIT.\n\nThe data is related to direct marketing campaigns of a Portuguese banking institution.\n\nYour task is to predict whether the client will subscribe to a term deposit.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric on submissions will be scored with a mean F1-score. The F1 score, commonly used in information retrieval, measures accuracy using precision (p) and recall (r). Precision is the ratio of true positives (TP) to all predicted positives (TP + FP). Recall is the ratio of true positives to all actual positives (TP + FN).\n\n$$\np = TP/(TP+FP), r = TP/(TP+FN), F_1 = 2.(p.r)/(p+r)\n$$\n\nTP: True Positive, FP: False Positive, TN: True Negative, FN: False Negative\n\nThe F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.\n\n---\n\n## Submission File\nFor each 'id' in the test set, you must predict the label for the 'subscribe' variable. The file should contain a header and have the following format:\n\n    id, subscribe\n    2,no\n    5,yes\n    6,no\n    etc.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": " - Don't cheat!\n - Apply yourself!\n - Have fun!\n - Creative solutions are encouraged!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Lab2",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "References",
      "content": "Moro,S., Rita,P., and Cortez,P.. (2012). Bank Marketing. UCI Machine Learning Repository. https://doi.org/10.24432/C5K306.\nNeha Patki, Roy Wedge, Kalyan Veeramachaneni. The Synthetic Data Vault. IEEE DSAA 2016.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}