{
  "fetched_at": "2026-10-20T04:33:49Z",
  "source_url": "https://www.kaggle.com/competitions/ctd-datawiz-2023/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Files Description\n\nThe data consists of three files:\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\n## Data Dictionary\n\n- **User ID**: Unique identifier for each telecom user.\n- **Mobile No.**: User's mobile phone number.\n- **User DOB**: Date of birth of the user.\n- **User Job**: Occupation or job of the user.\n- **Duration**: Total call duration (minutes) for the user.\n- **Intl_Plan**: Whether the user has an international calling plan (Yes/No).\n- **Voicemail_Plan**: Whether the user has a voicemail plan (Yes/No).\n- **Voicemail_Messages**: Number of voicemail messages received by the user.\n- **Day_Minutes**: Total minutes of daytime calls for the user.\n- **Day_Calls**: Total number of daytime calls made by the user.\n- **Day_Charge**: Total charge for daytime calls.\n- **Eve_Minutes**: Total minutes of evening calls for the user.\n- **Eve_Calls**: Total number of evening calls made by the user.\n- **Eve_Charge**: Total charge for evening calls.\n- **Night_Minutes**: Total minutes of nighttime calls for the user.\n- **Night_Calls**: Total number of nighttime calls made by the user.\n- **Night_Charge**: Total charge for nighttime calls.\n- **Intl_Minutes**: Total minutes of international calls for the user.\n- **Intl_Calls**: Total number of international calls made by the user.\n- **Intl_Charge**: Total charge for international calls.\n- **Service_Calls**: Number of user service calls made by the user.\n- **Attrition**: The target variable indicates user attrition (Yes/No).",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "# Problem Statement\n\nIn today's highly competitive telecom industry, retaining users is of paramount importance. Subscriber attrition, whether to competitors or due to dissatisfaction, can greatly affect a company's performance and profitability. Your objective is to build a predictive model that, given the historical data of telecom customers, can identify new users who are at risk of attrition in the near future.\n\n## Submission\n\nParticipants have to train their model on the training data (`train.csv`). The model has to be tested on the test data (`test.csv`). Finally, you have to make a submission file (refer to `sample_submission.csv` for the correct format) for the results predicted on the test data. Submit this file for evaluation on the platform.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The performance of your Machine Learning model will be evaluated on the basis of accuracy score.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "1. **Fair Play**: Play by the rules, and don't engage in cheating or unethical behavior.\n\n2. **Give Your Best**: Put in your best effort and showcase your skills.\n\n3. **Enjoy the Journey**: Have fun, learn, and enjoy the experience of competing and collaborating with others.\n\n4. **Respect Others**: Show respect for fellow participants, organizers, and the community.\n\n5. **Continuous Learning**: Embrace the opportunity to learn and grow as a data scientist.\n\n6. **Innovation Welcome**: Encourage creative solutions and innovative approaches.\n\n7. **Share Knowledge**: Share your knowledge and expertise with the Kaggle community.\n\n8. **Support Each Other**: Support and help fellow participants when possible.\n\n9. **Celebrate Diversity**: Embrace diversity and inclusivity in the data science community.\n\n10. **Stay Positive**: Maintain a positive attitude, even when facing challenges.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Read the overview of the competition before diving into it. All the best!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Prize",
      "content": "**1st Place**: ₹2000 💸 + Certificate 🏆\n\n**2nd Place**: ₹1000 💸 + Certificate 🏆\n\n**3rd Place**: Certificate 🏆\n\nYou are only eligible for prize money if you have played fair and you are registered for the DataWiz event. If not, you can register here: [CTD Website](http://ctd.credenz.in/events).\n\nFor SCTR's PICT students only!\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}