HOTEL ROOM BOOKING PREDICTION USING K-NEIGHBORS CLASSIFIER METHOD COMBINED WITH SLIDING WINDOWS
Trieu Vinh Khang , Le Duc Thang , Luc Ha Duy Nguyen, Ngo Ho Anh Khoi
Abstract: In a recovering economic situation after the epidemic, the problem of canceling bookings on a regular basis will cause losses for businesses. The problem of hotel booking cancellation causes many inconveniences for hotels and visitors, affecting revenue and customer's travel experience. The resolution of this issue is very necessary to ensure benefits for both sides and sustainable development of the tourism industry. Solving the problem of hotel cancellation plays an important role in life because it helps to create customer trust and satisfaction. At the same time, it also helps tourism develop sustainably and contribute to the development of the country's economy. The purpose is to provide entities with tools, research, and implementation results to address this problem through an artificial intelligence system, aiming to enhance the reliability of room bookings for both domestic and international businesses in Vietnam and around the world. The research aims to employ artificial intelligence systems to predict customer room booking needs conveniently. This project will help businesses easily understand the requirements of tourists, thus increasing revenue and contributing to the economic development of Vietnam and the global economy.
Keywords: Hotel Reservations Dataset, Hotel Reservation Prediction, Sliding Windows, Machine Learning, AI application.
Hotel Booking Attributes
| Attribute | Description | Minimum Value | Maximum Value |
|---|---|---|---|
| Label | Predicted results: 0 for no booking cancellation, 1 for booking cancellation | 0 | 1 |
| No. of Adults | Number of adults who have booked a room | 0 | 4 |
| No. of Children | Number of children included in the booking | 0 | 10 |
| No. of Weekend Nights | Number of weekend nights (Saturday or Sunday) the guests stayed | 0 | 7 |
| No. of Week Nights | Number of weekday nights (Monday to Friday) the guests stayed | 0 | 17 |
| Type of Meal Plan | Type of meal plan the customer has booked | Not Selected | Meal Plan 3 |
| Required Car Parking Space | Indicates whether the customer requested a parking space | 0 | 1 |
| Room Type Reserved | Type of room the guest has booked | Room Type 1 | Room Type 7 |
| Lead Time | Time from booking date to guest's arrival date at the hotel (days) | 0 | 443 |
| Arrival Year | Year the customer arrived at the hotel | 2017 | 2018 |
| Arrival Month | Month the customer arrived at the hotel | 1 | 12 |
| Arrival Date | Day of the month the customer arrived at the hotel | 1 | 31 |
| Market Segment Type | Specifies the market segment | Online | Aviation |
| Repeated Guest | Indicates whether the guest has stayed at the hotel before | 0 | 1 |
| No. of Previous Cancellations | Number of previous bookings that the customer had canceled before the current booking | 0 | 13 |
| No. of Previous Bookings Not Canceled | Number of previous bookings that the customer did not cancel before the current booking | 0 | 58 |
| Average Price per Room | Average price per room per day (in euros) | 0 | 540 |
| No. of Special Requests | Number of special requests made by the guest when booking the room | 0 | 5 |
CLICK TO KNOW MORE
