{
  "fetched_at": "2026-10-19T23:59:07Z",
  "source_url": "https://www.kaggle.com/competitions/dphi-amsterdam-airbnb-data/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## About the Data\nThe code competition data set can be found below. There are 3 different data sets available:\n\n- **airbnb_listing_train.csv:** this data set can be used to build and test your model. It contains all the variables including the variable that has to be predicted i.e. **price**. This dataset contains 12901 observations/records divided into 16 columns (including the target column - **'price'**)\n- **airbnb_listing_validate.csv:** this data set should be used to create the submissions. The data set contains all the variables that are also in the train data set except for the **'price'**.\n- **sample_submission.csv:** this is an example of what your submissions should look like. Note that there are no automatic checks performed on your uploaded file so make sure that your submission file matches this file perfectly. Also, note that the order in which observations are presented in the validation set must be preserved when delivering predictions.\n\nThe data sets have not been cleaned since this is an important step in creating a predictive model. Note also that there are many opportunities to engineer your own features. It is allowed to merge your data with other online data as long as you can make sure that your model also works on the validation data. Note also that the data sets are large so be aware of overfitting your models.\n\n## Feature Description\n- **id:** The id of each lodge/home/listing\n- **name:** The name/description of the lodge/home\n- **host_id:** The id of the host\n- **host_name:** Name of the host\n- **neighbourhood:** Name of the neighbourhood place\n- **neighbourhood_group:** Group in the neighbourhood\n- **latitude:** Latitude of the location\n- **longitude:** Longitude of the location\n- **room_type:** Type of the room that consumer booked, for example, private room or an entire home, etc.\n- **minimum_nights:** The minimum number of nights customer will stay\n- **number_of_reviews:** Number of reviews given to the lodge/home\n- **last_review:** The date of the last review given to the lodge/home\n- **reviews_per_month:** Average reviews per month\n- **calculated_host_listings_count:** The count of the listing that each host has\n- **availability_365:** The number of days (out of 365 days) for which lodge/home is available \n- **price:** Price for the lodging/homestays in USD - the target variable\n\n## Acknowledgement\nThis dataset is downloaded from Airbnb Inside.\n[http://insideairbnb.com/get-the-data.html](http://insideairbnb.com/get-the-data.html)\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "# Context\n**Airbnb, Inc.** is an American vacation rental online marketplace company based in San Francisco, California, United States. Airbnb offers arrangements for lodging, primarily homestays, or tourism experiences. The company does not own any of the real estate listings, nor does it host events; it acts as a broker, receiving commissions from each booking. [Reference](https://en.wikipedia.org/wiki/Airbnb)\n\nSince 2008, guests and hosts have used Airbnb to travel in a more unique, personalized way. \n\n# Objective\nImagine you are Data Scientist who would help find the price for lodging or homestays based on different attributes mentioned in their **listings**. Oh wait, **what are listings?** Listings can include written descriptions, photographs with captions, and a user profile where potential guests can get to know a bit about the hosts.\n\nAnd you are given the listings of one of the most popular cities in central Europe: Amsterdam. Now your job is to **build a machine learning model that will automatically predict the price for lodging or homestays.**\n\n# Acknowledgement\nThis dataset is part of Airbnb Inside, and the original source can be found [here](http://insideairbnb.com/get-the-data.html).\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "## Goal\nYour goal is to predict the price for lodging/homestay based on different attributes in the dataset. You can make a maximum of 20 submissions per day.\n\n## Metric\nThe evaluation metric for this competition is the Root Mean Squared Error (MSE). The RMSE is the square root of the averaged squared difference between the target value and the value predicted by the model.\n![RMSE Formula](https://miro.medium.com/max/520/0*TO7BkvQwtnvVzkK4.png)\n\nThe final winner of the competition will be determined based on a private leaderboard. A public leaderboard will also be available for the participants. In order to determine the score on the public leaderboard, 60% of the evaluation data is used. The other 40% of the evaluation data is used to create a private and final leaderboard. The team that ranks first on the private leaderboard is the winner of the competition. This team is not necessarily the team that ranked first on the public leaderboard.\n\n## What’s the difference between a private and public leaderboard?\nThe Kaggle leaderboard has a public and private component to prevent participants from “overfitting” to the leaderboard. If your model is “overfit” to a dataset then it is not generalizable outside of the dataset you trained it on. This means that your model would have low accuracy on another sample of data taken from a similar dataset.\n\n### Public Leaderboard\nFor all participants, the same 60% of predictions from the test set are assigned to the public leaderboard. The score you see on the public leaderboard reflects your model’s accuracy on this portion of the test set.\n\n### Private Leaderboard\nThe other 40% of predictions from the test set are assigned to the private leaderboard. The private leaderboard is not visible to participants until the competition has concluded. At the end of a competition, we will reveal the private leaderboard so you can see your score on the other 40% of the test data. The scores on the private leaderboard are used to determine the competition winners. Getting Started competitions are run on a rolling timeline so the private leaderboard is never revealed.\n\n## Submission File Format\nTo be added******",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "- You can only make submissions between 24th July - 11 pm and 29th July - 11:59 pm IST.\n- You can make any number of submissions in the entire competition limiting to 5 submissions per day, the submission with the best score will be considered as the final solution.\n- Sharing notebooks or code snippets with other participants is not permitted.\n- THE most important rule - have fun!\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Timeline",
      "content": "**Wednesday 29th of July:** Submission deadline at 23:59 hours UTC",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "FAQ",
      "content": "# What are Notebooks?\nKaggle Notebooks is a cloud computational environment that enables reproducible and collaborative analysis. Kernels support scripts in R and Python, Jupyter Notebooks, and RMarkdown reports. Go to the Notebooks tab to view all of the publicly shared code on this competition. For more on how to use Kernels to learn data science, visit the [Tutorials tab](https://www.kaggle.com/docs/notebooks). An example notebook has been provided in the Notebooks tab.\n\n# How do I submit my estimate?\nOnce you’re ready to make a submission and get on the leaderboard:\n\n1. Click on the “Submit Predictions” button\n2. Upload a CSV file in the submission file format. You’re able to submit 5 submissions a day.\n3. Submission File Format: you should submit a CSV file with exactly 6451 entries plus a header row. The file should have exactly 2 columns: Id and predicted price.\n\n# What are the different datasets for?\nThere are two different datasets (and a sample submission) available in the Data tab. The 'airbnb_listing_train.csv' dataset should be used to develop and test your model.  Once your model is properly tested you have to use the 'airbnb_listing_validate.csv' dataset to create your submission file.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}