{
  "fetched_at": "2026-10-24T16:46:50Z",
  "source_url": "https://www.kaggle.com/competitions/copy-of-max-indabax-nigeria-hackathon/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The data consist of the social and demographic nature of the max drivers.\n\n## 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\n**Note** you must submit a probability prediction.\n\n## Columns\n\n*   `ID` - Unique identify\n*   `subscriber_id` - subscriber id\n*   `date_time` - The date of the onboarding\n* `agent_id` - agent id\n* `entry_channel_id` - entry channel id\n* `stage_status` - stage status\n* `subscriber_age` - Age of the subscriber\n* `gender` - gender\n* `city` - city\n* `label` - The label you will predict for the test data.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Predict the likelihood of a lead reaching the last stage (onboarding) quicker than others. This will enable the team to channel resources and efforts toward converting such leads.\nThe model that says the type of leads to after, so we don’t waste resources. (In terms of age, geography, marital status, and other lead qualities)\n\nYour task is to build machine learning to help the business in saving costs.\n\nNote: Maximum Submission per day Predict the likelihood of a lead reaching the last stage (onboarding) quicker than others. This will enable the team to channel resources and efforts toward converting such leads.\nThe model that says the type of leads to after, so we don’t waste resources. (In terms of age, geography, marital status, and other lead qualities)\n\nYour task is to build machine learning to help the business in saving costs.\n\nNote: Maximum Submission per day is 20. Kindly have good cross validation to optimise your solution and submission.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "---\n\nThe evaluation metric for this competition is [Log Loss.](https://en.wikipedia.org/wiki/Loss_functions_for_classification).\n\n## Submission Format\n\n**For every row in the dataset**, submission files should contain 12 columns: `ID` and Each training data label probabilities.\n\nThe file should contain a header and have the following format:\n```\nID,Activated,Awaiting Activation..., Top of the funnel\n'ID_04....',0.0,0.0,0.0\n```\n\n**Note** Your submission must be in probabilities.\nUse **model.predict_proba()**",
      "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- The dataset must not be shared or disclosed to a non-register participant.\n- The dataset NDA form must be filled before the commencement of the hackathon.\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Prize",
      "content": "6 months paid internship with Max.ng for the 1st, 2nd, and 3rd position.\n\n1st - 6 months paid internship\n\n2nd - 6 months paid internship\n\n3rd - 6 months paid internship.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}