{
  "fetched_at": "2026-10-19T19:04:04Z",
  "source_url": "https://www.kaggle.com/competitions/79-dapt-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": "Booking cancellations often directly impact a hotel's bottom line: many times the room(s) reserved are not booked again, resulting in lower occupation and, subsequently, revenue. To hedge this risk, hotels often demand a booking deposit, often calculated as a percentage of the reservations full price. However, this practice can directly impact demand as some customers might look for different hotels with no deposit (or a smaller one). Our goal is to build a model that, by predicting whether a booking will be cancelled or not, can be used by the hotel to implement different risk-aware strategies for calculating the deposit size. \n\nLet's use our recently acquired ML skillset to build a classifier! In this case we've been asked to create a model predicting booking cancellations in 2 different hotels. The data utilized here is real world anonymized data.\n\nData source:  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
    }
  ]
}