{
  "fetched_at": "2026-10-19T19:04:05Z",
  "source_url": "https://www.kaggle.com/competitions/99-dapt-sao-ih-hotel-booking/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The files provided are:\n\n- Training set (`tb_hotel_traintest.csv`) with all features and the response variable (`is_cancelled`)\n- Validation set (`tb_hotel_feat_valid.csv`) with all features for making predictions\n- Sample submission (`tb_hotel_sample_valid.csv`), which is an example of the file you must submit with predictions made from the validation set.\n\nThe PDF file contains more extensive description of each variable in the dataset.\n\n## Files\n\n*   **tb_hotel_traintest.csv** - the training set\n*   **tb_hotel_feat_valid_2.csv** - the validation set\n*   **tb_hotel_sample_valid.csv** - a sample submission file in the correct format\n\n## Columns\n\n* **hotel** - (str) Tipo de hotel.\n* **is_cancelled** - (binary) Variável binária indicando cancelamento da reserva (0 = não cancelada, 1 = cancelada) - variável resposta do case.\n* **lead_time** - (int) Número de dias entre data da reserva e data de entrada no hotel (quando a reserva foi feita).\n* **arrival_date** - (date) Data de entrada no hotel (para quando a reserva é).\n* **stays_in_weekend_nights** - (int) Número de dias em finais de semana na reserva.\n* **stays_in_week_nights** - (int) Número de dias de semana na reserva.\n* **adults** - (int) Número de adultos.\n* **children** - (int) Número de crianças.\n* **babies** - (int) Número de bebes.\n* **meal** - (str) Tipo de refeição inclusa na reserva.\n* **country** - (str) País do cliente.\n* **market_segment** - (str) Segmentação de marketing do cliente.\n* **distribution_channel** - (str) Canal de vendas pelo qual a reserva foi feita.\n* **is_repeated_guest** - (binary) O cliente já ficou hospedado no hotel? (0 = não, 1 = sim).\n* **previous_cancellations** - (int) Quantas reservas o cliente já cancelou no passado.\n* **previous_bookings_not_canceled** - (int) Quantas reservas o cliente já fez e não cancelou no passado.\n* **reserved_room_type** - (str) Tipo de quarto desejado.\n* **assigned_room_type** - (str) Tipo de quarto reservado.\n* **booking_changes** -  (str) Número de mudanças na reserva entre data de reserva e entrada/cancelamento.\n* **deposit_type** - (str) Tipo de adiantamento feito no momento da reserva.\n* **agent** - (str) ID do Agente que fez a reserva (NA caso a reserva não tenha sido feita por um agente).\n* **company**  - (str) ID da empresa que fez a reserva (NA caso a reserva não seja corporativa)\n* **days_in_waiting_list** - (int) Quantos dias demorou a confirmação da reserva.\n* **customer_type** - (str) Tipo de reserva.\n* **adr** - (float) Average Daily Rate, preço médio de cada diária na reserva.\n* **required_car_parking_spaces** - (int) Número de vagas em estacionamento requisitadas na reserva.\n* **total_of_special_requests** - (int) Número de requisições especiais na reserva (cama dupla, andar, quarto com vista...)\n* **reservation_status_date** - (date) Data da última atualização feita na reserva.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## Hotel Booking Cancellations Prediction\n\nBooking cancellations can have a significant impact on a hotel's revenue and bottom line. When a reservation is cancelled, the hotel may not be able to book that room again, resulting in lost revenue. To mitigate this risk, hotels often require a booking deposit, which is usually a percentage of the reservation's full price. However, requiring a deposit can also have negative consequences, such as *dissuading some customers from booking at the hotel altogether*.\n\nTo address this challenge, our Kaggle competition aims to **build a predictive model that can accurately determine whether a hotel booking will be cancelled or not**. By predicting cancellations in advance, hotels can implement risk-aware strategies for calculating deposit sizes and making other operational decisions that help them **maximize occupancy rates and revenue**.\n\n### The Challenge\n\nIn this competition, you will work with **real-world anonymized data from two different hotels** to develop a model that predicts whether a booking will be cancelled or not. The data set includes a range of features, such as:\n\n- The booking date\n- The length of the stay\n- The number of guests\n- And other relevant information that can help inform the model's predictions\n\nYour challenge is to create a **classifier that accurately predicts whether a given booking will be cancelled or not**.\n\n### The Goal\n\nBy participating in this Kaggle competition, you will have the opportunity to:\n\n- Apply your machine learning skills to a **real-world business problem**\n- Develop **innovative solutions** that can help hotels improve their revenue and bottom line\n- **Showcase your skills** and learn from other participants\n\nWhether you're an experienced data scientist or a newcomer to the field, this competition offers a challenging and rewarding opportunity to showcase your skills and learn from other participants. \n\nSo, **join us today and start building your predictive model for hotel booking cancellations!**\n\n# Data \n\n[Data in Brief](https://www.sciencedirect.com/science/article/pii/S2352340918315191)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is [Mean F1-Score](https://en.wikipedia.org/wiki/F-score). The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision \\( \\text{p} \\) and recall \\( \\text{r} \\).\n\nPrecision is the ratio of true positives \\(\\text{tp}\\) to all predicted positives \\(\\text{tp} + \\text{fp}\\). Recall is the ratio of true positives \\(\\text{tp}\\) to all actual positives \\(\\text{tp} + \\text{fn}\\). The F1 score is given by:\n\n\\[ \\text{F1} = 2\\frac{\\text{p} \\cdot \\text{r}}{\\text{p}+\\text{r}}\\ \\ \\mathrm{where}\\ \\ \\text{p} = \\frac{\\text{tp}}{\\text{tp}+\\text{fp}},\\ \\ \\text{r} = \\frac{\\text{tp}}{\\text{tp}+\\text{fn}} \\]\n\nThe F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.\n\n## Submission Format\n\n**For every id_booking in the validation dataset** provide a binary prediction of the cancellation status (`is_cancelled` in the training dataset). The file provided must have two columns:\n\n- **id_booking** from the validation set\n- **is_cancelled** from your predictions.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "- Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}