{
  "fetched_at": "2026-10-19T19:38:45Z",
  "source_url": "https://www.kaggle.com/competitions/criticalitypredictioninsurance/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The training dataset has 120 predictor variables which are annonymized and a target variable named ‘Label’\n\nThe test dataset has no target variable\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",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Insurance companies play an important role in providing financial support to the insured in the event of unforeseen events like critical illness, hospitalization, accidents or death. \nInsurers face the challenge of determining the amount of premium to be paid by the insured. \nTo accurately estimate this, extensive background checks are required to be done by the insurer. The most important is to determine the “***level of criticality***” or the probability of a critical illness occurring in a prospective insurance customer. \nAdding to the challenge is that background checks are done by humans and human error/ bias cannot be ruled out. If background checks are not done at all or not reported correctly, this can result in an extraordinary liability for the insurer. \nIn the event of an unfortunate eventuality of the insured, the insurance company is liable to pay a hefty amount in excess of the premium collected.\nIn view of this it is important that the probable criticalities be predicted by a machine learning model accurately. This will enable the turnaround time of insurance approval and disbursal of claims to get crashed leading to higher efficiency in operations.\nBefore issuing the insurance policy bond, insurers record multiple data points related to family background, medical history, economic strata and other related data. These are processed manually to estimate the criticality score of the insured. \nFor this competition the data is in an excel file. The objective is to predict the criticality level or score of the potential prospect for insurance (the last variable in the training set). The variables are anonymized for security reasons. \n\n\n\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are scored based on the quadratic weighted kappa, which measures the agreement between two ratings. This metric typically varies from 0 (random agreement between raters) to 1 (complete agreement between raters). In the event that there is less agreement between the raters than expected by chance, this metric may go below 0. The quadratic weighted kappa is calculated between the scores assigned by the human rater and the predicted scores.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Hackathon is open to students from colleges in the East Zone only\nThe competition will open on 21st October and registrations/ entries will remain open till 20th December",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Prizes",
      "content": "The top 3 will be awarded cash prizes of Rs. 25K; Rs. 15K & Rs. 10K respectively. Totalling Rs. 50K",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}