Booking Cancellation Prediction with Classification Model

He, Haokun (2020) Booking Cancellation Prediction with Classification Model. [Dissertation (University of Nottingham only)]

[img] PDF - Repository staff only - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (508kB)


Booking cancellation prediction becomes more significant than before, which impacts

decision making in the hospitality industry. In the revenue management system, with

inaccurate prediction of hotel demand, overbooking and cancellation policy might lead to a

negative influence on the operation of the hotel and reputation of the hotel.

Using PMS data and external data, addressing the booking cancellation problem as a

classification problem, the author used different algorithms and different models to get the

highest accuracy, the result was exceeding 0.89, which shows the hotel industry can predict

whether a booking is likely to be canceled with high accuracy.

Models allow the hotel industry to make different actions on overbooking and cancel booking

based on which factors were most important in the model. A high accuracy model can prevent

the enterprise from reputation and profit losing. Moreover, there will be some future research

suggestions provided in the end.

Keyword: Data science, booking cancellation, hospitality industry, machine learning,

predictive modeling, revenue management, weather, distance, classification

Item Type: Dissertation (University of Nottingham only)
Depositing User: HE, Haokun
Date Deposited: 13 Dec 2022 17:04
Last Modified: 13 Dec 2022 17:04

Actions (Archive Staff Only)

Edit View Edit View