{
  "fetched_at": "2026-10-19T19:03:57Z",
  "source_url": "https://www.kaggle.com/competitions/dev-comm-ml-recruitment/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Files\n\n*   **train.csv** - the training set\n*   **test.csv** - the test set \n \n## Columns\n\n*   `id` -  unique identication no. for each record\n*   `latitude` -  Center of 1km fire pixel but not necessarily the actual location of the fire as one or more fires can be detected within the 1km pixel.\n*    `longitude` -  Center of 1km fire pixel but not necessarily the actual location of the fire as one or more fires can be detected within the 1km pixel.\n*    `brightness` -  Brightness temperature 21 (Kelvin): Channel 21/22 brightness temperature of the fire pixel measured in Kelvin.\n*    `scan` -  The algorithm produces 1km fire pixels but MODIS pixels get bigger toward the edge of scan. Scan and track reflect actual pixel size.\n*    `track` - The algorithm produces 1km fire pixels but MODIS pixels get bigger toward the edge of scan. Scan and track reflect actual pixel size. \n*    `acq_date` -  Date of MODIS acquisition.\n*    `acq_time` - Time of acquisition/overpass of the satellite (in UTC).\n*    `satellite` - type of the satellite\n A = Aqua and T = Terra.\n*    `instrument` -  Constant value for MODIS.\n*    `confidence` -   (0-100%): This is target column. This value is based on a collection of intermediate algorithm quantities used in the detection process. It is intended to help users gauge the quality of individual hotspot/fire pixels. Confidence estimates range between 0 and 100%.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": " ## Evaluation Criteria\nThe ranking in this competition will be based on the R² score of the models. The R² score, also known as the coefficient of determination, measures how well your model's predictions match the actual values. The higher the R² score, the better your model performs.\n\n ## Submission File\nFor each ID in the test set, you must predict a probability for the 'confidence' variable. The file should contain a header and have the following format:\n\n    id,confidence\n    2,0\n    5,0\n    6,0\n    etc.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Eligibility:\n\nThe competition is open to all members of Devcomm, NSUT.\n\n- Participants must compete individually.\n\n- Original Work:\n\nAll submissions must be the original work of the participant.\nDo not use external code or solutions that are not your own.\n\n- Data Usage:\n\nUse only the provided dataset for training your models.\nExternal data is not permitted unless explicitly stated in the competition guidelines.\n\n- Submission Limit:\n\nEach participant or team is allowed a maximum of 12 submissions per day.\nMake sure your final submission is your best attempt.\n\n- Evaluation:\n\nSubmissions will be evaluated based on accuracy\nThe leaderboard will reflect the scores of your best submission.\n\n- Cheating:\n\nDo not attempt to manipulate the competition in any way.\nPlagiarism, including using code from previous competitions, will result in disqualification.\n \n- Confidentiality:\n\nDo not share your code or solutions publicly during the competition. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Welcome to the Devcomm Machine Learning Recruitment Competition! We are excited to see your skills in action as you tackle a real-world problem with significant environmental and societal impact. This competition will serve as a platform for you to demonstrate your machine learning prowess and innovative thinking.\n\n#Competition Overview\n\nIn this competition, your task is to predict the confidence level of forest fires. The confidence level is a measure of how likely it is that a fire has occurred in a specific area based on various environmental factors. Accurate predictions can help in early detection and efficient allocation of resources to combat forest fires.\n\n# Problem Statement\nForest fires are a critical environmental issue that can cause massive destruction to ecosystems, wildlife, and human settlements. Your objective is to develop a machine learning model that predicts the confidence level of forest fires using provided datasets.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}