{
  "fetched_at": "2026-10-20T09:39:55Z",
  "source_url": "https://www.kaggle.com/competitions/aai-bike-rental-prediction/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Description of columns in the dataset\n* instant: record index\n* dteday : date\n* season: season (1:winter, 2:spring, 3:summer, 4:fall)\n* year:  (0: 2011, 1:2012)\n* month: month ( 1 to 12)\n* holiday: weather day is holiday or not (extracted from [Web Link])\n* weekdaynum: day of the week\n* is_workingday: if day is neither weekend nor holiday is 1, otherwise is 0.\n*weathersituation:\n - 1: Clear, Few clouds, Partly cloudy, Partly cloudy\n - 2: Mist + Cloudy, Mist + Broken clouds, Mist + Few clouds, Mist\n - 3: Light Snow, Light Rain + Thunderstorm + Scattered clouds, Light Rain + Scattered clouds\n - 4: Heavy Rain + Ice Pallets + Thunderstorm + Mist, Snow + Fog\n* atemp_normalized: Normalized feeling temperature in Celsius. \n  - The values are derived via (t-tmin)/(tmax-tmin), tmin=-16, t_max=+50 (only in hourly scale)\n* humidity_normalized: Normalized humidity. The values are divided to 100 (max)\n* windspeed_normalized: Normalized wind speed. The values are divided to 67 (max)\n* total_rental: count of total rental bikes including both casual and registered\n\nTrain a regression model to predict the total rental count, based on relevant variables per your understanding\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",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## Problem Statement :\nBike sharing systems are new generation of traditional bike rentals where whole process from membership, rental and return back has become automatic. Through these systems, user is able to easily rent a bike from a particular position and return back at another position. \n\nCurrently, there are about over 500 bike-sharing programs around the world which is composed of over 500 thousands bicycles. Today, there exists great interest in these systems due to their important role in traffic, environmental and health issues.\n\nThe data each day on number of bikes rented and other associated variables are recorded by a company in South Korea to understand the demand for such service.\n\n###  Task:\n- Train a model to predict total_rentals using train.csv. \n- Predict total_rentals for data provided in test.csv using the trained model.\n- Upload the prediction file with 1 column named total_rental.\n\n### Rules:\n - You can submit up to 5 solutions per day. The final submission deadline is 4th June at 5:00 PM.\n - Submissions file has to be uploaded on Kaggle. Check sample submission for reference.\n\n### Evaluation:\n  - RMSE is the evaluation criteria. Lower the RMSE, better is the solution.\n\n### Results: \n - Public leader board will display the score, while competition is in progress.\n - Final results will be displayed in private leader board after the competition closes. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "---\n\nThe evaluation metric for this competition is [RMSE] (https://en.wikipedia.org/wiki/Root-mean-square_deviation). \n\n## Submission Format\n\n**For every author in the dataset**, submission files should contain only one columns: `total_count` \n\nThe file should contain a header and have the following format:\n```\nID, total_count\nA601, 7456\nA602, 4532\nA603, 3457\nA604, 6541\n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a individual exercise. \n- Do not take help from others\n- Think through the problem before working on it.\n- Data analysis is as important as modeling. Don't ignore it.\n- Have fun !! 👍 ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}