| Author: | Wang, Qiulin |
| Title: | How does multi-attribute decision-making drive Hong Kong inbound Chinese tourists’ online hotel choice? – A random forest analysis |
| Advisors: | Leung, Daniel (SHTM) Law, Rob (SHTM) |
| Degree: | Ph.D. |
| Year: | 2021 |
| Subject: | Hotels Hotels Hospitality industry Hong Kong Polytechnic University -- Dissertations |
| Department: | School of Hotel and Tourism Management |
| Pages: | xv, 203 pages : color illustrations |
| Language: | English |
| Abstract: | Hotel choice decision is one of the most researched areas in hospitality and even business fields. Although a plethora of research has been conducted and diversified issues have been examined, several research gaps can still be identified: (1) with the rapid development of online booking channels, there is a need to systematically re-examine the influence of hotel attributes on consumers' hotel choice that existing in an online setting; (2) a hotel choice includes sequential decisions of considering different attributes at different priority levels, it is unclear how consumers prioritize attributes in the formation of the consideration-set stage and the final choice decision stage during the hotel choice process; (3) adequate number of hotel alternatives should be given to stimulate the real market instead of questioning consumers about their purchase intention directly or/and giving them only a small range of hotel choices; (4) a systematic prediction method should be used to predict hotel choice. In recognition of the research gaps mentioned above, this study aims to complement the growing stream of research on hotel choice by investigating "which and how hotel attributes affect consumers' formation of consideration set and final choice?". This study assumes individuals are limited rational decision-makers with limited information processing capacity. A scenario-based experimental design approach was employed to simulate consumers' online hotel choice process. The Random Forest algorithm was applied to depict the relationship between consumers' online hotel choice and a set of explanatory attributes. These explanatory attributes are customer rating, review volume, room rate, agency rating, accessibility to the transportation, accessibility to the city center, location, cancellation policy, check-in and check-out time, renovated time and hotel facilities (including swimming pool, fitness center, airport shuttle, parking and restaurant). Harnessing the Random Forest algorithm, this study is designed to present a multi-stage and multi-attribute choice model based on the knowledge of information processing theory, phased decision theory and multi-attribute decision-making theory. The model is developed on the notion that consumers consider different attributes at different priority levels during their online hotel choice process. The findings show that at the formation of the consideration-set stage, accessibility to the city center, review volume, room rate, renovated time and customer rating are the top five important attributes. At the formation of the final choice decision stage, room rate, review volume, accessibility to the city center, customer rating and location are the top five important attributes. The findings in this study contribute new knowledge to the growing hotel choice literature by adopting a machine learning approach to examine hotel attributes' importance level. Besides, hotel practitioners may benefit from improving the navigation of online booking websites and adopting relevant marketing strategies. |
| Rights: | All rights reserved |
| Access: | open access |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/11563