{
  "fetched_at": "2026-10-20T00:46:03Z",
  "source_url": "https://www.kaggle.com/competitions/bank-customer-churn-prediction-spark4ai/data",
  "pages": [
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated on [area under the ROC curve](http://en.wikipedia.org/wiki/Receiver_operating_characteristic) between the predicted probability and the observed target.\n\n\n## Submission File\nFor each `id` in the test set, you must predict the probability for the target variable `Exited`. The file should contain a header and have the following format:\n\n    id,Exited\n    165034,0.9\n    165035,0.1\n    165036,0.5\n    etc.",
      "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 - Sole purpose of this competition is to learn new techniques!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "The dataset for this competition (both train and test) was generated from a deep learning model trained on the [Bank Customer Churn Prediction](https://www.kaggle.com/datasets/shubhammeshram579/bank-customer-churn-prediction) dataset. Feature distributions are close to, but not exactly the same, as the original. Feel free to use the original dataset as part of this competition, both to explore differences as well as to see whether incorporating the original in training improves model performance.\n\n## Files\n\n*   **train.csv** - the training dataset; `Exited` is the binary target\n*   **test.csv** - the test dataset; your objective is to predict the probability of `Exited`\n*   **sample_submission.csv** - a sample submission file in the correct format",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "**Welcome to the Bank Customer Churn Prediction Competition !** This is the near-replica of one of the [Kaggle Playground Series Competition](https://www.kaggle.com/competitions/playground-series-s4e1). The objective to host a pre-existing competition was to provide enough resources for newbies in this field to have access to almost all the state of the art techniques to build great models for real word datasets, also ensuring fair play [as the dataset for training and evaluation is synthetically generated and not publicly available, and very near to the feature distributions what we see in real world datasets].\n\n**Your Goal:** Your task is to predict whether a customer continues with their account or closes it (e.g., churns). Good luck!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}