{
  "fetched_at": "2026-10-20T00:16:50Z",
  "source_url": "https://www.kaggle.com/competitions/data-science-2-2024-hw1/data",
  "pages": [
    {
      "name": "data-description",
      "content": "We have two datasets:\n\n2024_DS2_HW1_data_train.csv: reservation attributes together with the target (binary variable booking_status) to be used for model training\n2024_DS2_HW1_data_test.csv: reservation attributes without the target to be used as underlying data for prediction and model performance evaluation\n\nData Dictionary\n\nBooking_ID: unique identifier of each booking\nno_of_adults: Number of adults\nno_of_children: Number of Children\nno_of_weekend_nights: Number of weekend nights (Saturday or Sunday) the guest stayed or booked to stay at the hotel\nno_of_week_nights: Number of week nights (Monday to Friday) the guest stayed or booked to stay at the hotel\ntype_of_meal_plan: Type of meal plan booked by the customer:\nrequired_car_parking_space: Does the customer require a car parking space? (0 - No, 1- Yes)\nroom_type_reserved: Type of room reserved by the customer. The values are ciphered (encoded) by INN Hotels.\nlead_time: Number of days between the date of booking and the arrival date\narrival_year: Year of arrival date\narrival_month: Month of arrival date\narrival_date: Date of the month\nmarket_segment_type: Market segment designation.\nrepeated_guest: Is the customer a repeated guest? (0 - No, 1- Yes)\nno_of_previous_cancellations: Number of previous bookings that were canceled by the customer prior to the current booking\nno_of_previous_bookings_not_canceled: Number of previous bookings not canceled by the customer prior to the current booking\navg_price_per_room: Average price per day of the reservation; prices of the rooms are dynamic. (in euros)\nno_of_special_requests: Total number of special requests made by the customer (e.g. high floor, view from the room, etc)\nbooking_status: Flag indicating if the booking was canceled or not.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## Task\nIn this assignment we have data about online hotel reservations (train dataset). A number of reservations are called-off due to cancellations or no-shows for any reason.\n\nCan you predict if the customer is going to honor the reservation or cancel it?\n\nMore specifically,\n* build a model to predict *booking_status* using xgboost.XGBClassifier\n* use data transformations/encoding and hyperparameters of the model to obtain best results possible while keeping the number of predictors reasonably low\n* to keep the number of predictors low you should assess their strength and explore if they add some value to the model\n* use the test dataset to compute predictions and submit your results\n\n## Expected outcomes\n\nUntil the competition deadline you are supposed to\n* Submit solution in this competition\n* Send either .py or .ipynb file with working (and reasonably readable and commented) code that leads to the prediction to tybl@karlin.mff.cuni.cz. \n* The code has to be runnable and it should be clear how you obtained the final predictions and how you assessed used predictors (why you dropped the predictors you dropped and why you used the predictors you used)\n* Send the script zipped and named as DS2\\_24\\_HW1\\_XXX.zip, where XXX is the name of your team in this Kaggle competition. Use the same naming convention for the script and for the mail subject. Clearly indicate your names in the body of the mail.\n\nAfter the competition deadline, the script of submissions will be revised. It may happen that you will be asked to correct some mistakes and/or answer some questions in some given period. Only after that the submission is considered is accepted.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "## Metric The evaluation metric for this competition is AUC (area under the curve). \n\nThe AUC score, commonly used in credit risk tasks, measures performance of models for prediction of binary targets. You shall use sklearn package to evaluate the metric on your train dataset. See https://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_auc_score.html \n\n## Submission Format \n\nSubmission csv should contain two columns: \n* **Booking\\_ID** - column ID for the observation \n* **prediction** - column consisting of the predicted value Submission was tested using comma separated csv format.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": " - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": " ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}