{
  "fetched_at": "2026-10-19T11:55:21Z",
  "source_url": "https://www.kaggle.com/competitions/gis-3-machine-learning-lab-2020/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<h3>Data Sources </h3>\nThe location of the parked cars was extracted from the AutoTel website, every two minutes for several weeks. The raw data was saved in CSV format. In this lab, there are 4 csv files provided: \n</br></br>\n- <b>car_location_training.csv</b> : Contains the training data that you need. These are the raw data collected from the AutoTel website. In this lab, we will process these raw data step by step and use it for forecasting the daily car rental demand.\n</br>\n-  <b>car_location_testing_daily_withoutLable.csv </b> : Contains the data that you need to predict. It has more column then the training set as we have aggrated t the data as daily records and provided the number of parking spots in the new car station. The prediction results need to be submitted for the in-class competition.  \n</br>\n- <b>tel_aviv_neighborhood.csv</b> : Contains the data that you need for visualization.\n</br>\n-  <b>sample_submission.csv </b>: A sample of what you should upload for the competition. The sample submission file contains the results from a dummy model. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Car sharing service allows car renting and returning via a network of stations located throughout the city. The data generated by these systems is explicitly recorded and could be used for analysis. Car sharing systems, therefore, function as a sensor network, which can be used for studying mobility in a city. Now, we have collected the historical usage patterns and decided to use it for forecasting car rental demand for building a new station in the city.\n<hr>\n\n###Acknowledgements\nThe dataset used in this lab was provided by Gad Benram using the data from AutoTel car sharing (https://www.kaggle.com/gidutz/autotel-shared-car-locations).\n\n<div>Icons made by <a href=\"https://www.flaticon.com/authors/surang\" title=\"surang\">surang</a> from <a href=\"https://www.flaticon.com/\" title=\"Flaticon\">www.flaticon.com</a></div>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<h2>Evaluation</h2>\nSubmissions are evaluated one the Root Mean Squared Error (RMSE). You could find your submission scores in **public leaderboard** (calculated with 40% of the test data) and **private leaderboard** (calculated with 60% of the test data after the deadline of this competition).\n\n<h2>Submission Format</h2>\n<p>Your submission file must have a header and should be structured in the following format:</p>\n<pre> Index,daily_car_demand<br> 0,0<br> 1,0<br> 2,0<br> ... <br> ... </pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "<h2>Team Limits</h2>\nYou should do it individually.\n\n<h2>Submission Limits</h2>\nYou may submit a maximum of 20 entries per day. \nYou may select up to 5 final submissions for judging.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}