A Framework of Improving the Design of Tourism Demand Forecasting
Total Page:16
File Type:pdf, Size:1020Kb
Copyright Undertaking This thesis is protected by copyright, with all rights reserved. By reading and using the thesis, the reader understands and agrees to the following terms: 1. The reader will abide by the rules and legal ordinances governing copyright regarding the use of the thesis. 2. The reader will use the thesis for the purpose of research or private study only and not for distribution or further reproduction or any other purpose. 3. The reader agrees to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage. IMPORTANT If you have reasons to believe that any materials in this thesis are deemed not suitable to be distributed in this form, or a copyright owner having difficulty with the material being included in our database, please contact [email protected] providing details. The Library will look into your claim and consider taking remedial action upon receipt of the written requests. Pao Yue-kong Library, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong http://www.lib.polyu.edu.hk The Hong Kong Polytechnic University School of Hotel and Tourism Management Improving the Design of Tourism Demand Forecasting Support System Zixuan Gao A thesis submitted in partial fulfilment of the requirements for the degree of Doctor of Philosophy 04/2015 CERTIFICATE OF ORIGINALITY I hereby declare that this thesis is my own work and that, to the best of my knowledge and belief, it reproduces no material previously published or written, nor material that has been accepted for the award of any other degree or diploma, except where due acknowledgement has been made in the text. ___________________________ (Signed) Zixuan Gao (Name of student) I ABSTRACT Accurate tourism demand forecast is the foundation of all tourism-related businesses. As a particular type of decision support system, forecasting support systems (FSS) have been widely applied in tourism demand forecasting in recent years. One of the typical characteristics of existing tourism demand forecasting support systems (TDFSS) is the combination of statistical and judgmental forecasting techniques. A review of recent studies in this area shows that most studies on the development of TDFSS focus on the improvement of statistical forecasting methods. The effectiveness of human participation in the forecasting process is largely neglected, especially the influence of forecasters’ cognitive bias on forecast accuracy during the judgmental forecasting process when using TDFSS. Focusing on three typical cognitive biases (desire bias, anchoring bias, and overconfidence bias) in the literature of judgmental forecasting, this study represents the first attempt to identify the influence of these three cognitive biases on the judgmental forecasting of tourism demand and how they affect forecast accuracy. The second purpose of this study is to propose a systematic debiasing model that is able to effectively reduce the forecast error associated with the identified cognitive biases and can be easily implemented in the design of TDFSS. The proposed debiasing model comprises two parts: cognitive bias detection and debiasing. In the first part, potential cognitive biases involved in forecasters’ judgmental forecasts can be detected with a series of post-hoc tests. Based on the typical design features of FSS, both informative guidance and suggestive guidance are used as the debiasing strategies in the second part of the model. To test its effectiveness and related hypotheses, the proposed debiasing model has been implemented in the design of the Hong Kong tourism demand forecasting support system (HKTDFS). A two-stage laboratory experiment using HKTDFS and the empirical data of international tourist arrivals to Hong Kong from 10 destination-origin (D-O) pair markets was conducted. The experiment proceeded in three sessions and 75 qualified forecasters agreed to participate. Ultimately, 68 participants provided qualified data for further analysis. II The results show that 14 of 21 hypotheses are supported, one is partially supported, and the remaining six are rejected. Generally, the three cognitive biases examined are common in judgmental forecasting of tourism demand and contribute significantly to forecast error. Both performance feedback (PF) and system-suggested forecasts are effective in eliminating the influence of cognitive bias on forecast accuracy. In the design of TDFSS, these two debiasing strategies should be used in dealing with different cognitive biases. To be specific, PF should be provided to forecasters when desired outcome-related cognitive biases are detected; system-suggested forecasts should be recommended to replace forecasters’ judgmental forecasts when forecasters anchor their judgmental forecast on the statistical forecast or the latest observation of the forecasting series. In extreme cases, when system-suggested forecasts are not available, keeping statistical forecasts unchanged is the backup strategy when forecasters anchor their judgmental forecasts on statistical forecast; Naïve I forecast is the backup strategy when forecasters anchor on the latest observation of the forecasting series. These results provide evidence to further revise the debiasing model in order to improve the design of TDFSS. Keywords: forecasting support system, tourism demand, judgmental forecasting, cognitive bias, desire bias, anchoring bias, overconfidence, debiasing, decision guidance III ACKNOWLEDGEMENTS I would like to express my warmest and sincere gratitude to my chief supervisor Prof. Haiyan Song for his continuous support of my study. His invaluable guidance always be a lantern in the dark when I facing difficulties in my research and thesis writing. The completion of this thesis would even been impossible without his persistent help and encouragement throughout the whole life periods of my Ph.D. study. My sincere thanks also go to the faculty members and my colleagues in the school of Hotel and Tourism Management (SHTM) for their insightful comments and suggestions on my study. Special thanks to Prof. Rob Law for his guidance and kind suggestions at the starting stage of my research; thanks to Dr. Alan Wang and Dr. Kam Hung for their great support in the phase of data collection. Thanks to my fellow research mates in SHTM: Dr. Yong Chen, Dr. Lily Sun, Dr. Rosanna Leung, Emmy, and Louisa, and Daniel for the helpful discussions and bright ideas related to my research. I would also like to express my gratitude to my BoE Chair Dr. Karin Weber and my external examiners Prof. Honggang Xu from Sun Yat-sen University (China) and Dr. Bing Pan from the College of Charleston (US). Their comments are valuable for me to further improve my thesis. My appreciations also goes to researchers from oversea universities and colleagues who provided patient guidance and direction on the improvement of my research design during the period of attachment programme in the United Kingdom. My special thanks to Prof. Gang Li from the University of Surrey, and Prof. Robert Filds, Dr. Sven F. Crone, Dr. Fotios Petropoulos, Dr. Nikolaos Kourentzes, and Dr Gokhan Yildirim from Lancaster University. IV Furthermore, thanks to my beloved friends' support during my Ph.D. life. Special thanks to Ms. Baijing Song, Mr. Louis Shih, and Dr. Eve Ren who have been giving their consistent support in many different ways. Lastly, I would like to express my deepest appreciation to my wife, my parents, and all relatives who shared their love and wholehearted support in my four-year research period. You are truly my spiritual pillars and this thesis is for all of you. V TABLE OF CONTENTS CERTIFICATE OF ORIGINALITY .................................................................................. I ABSTRACT ...................................................................................................................... II ACKNOWLEDGEMENTS ............................................................................................. IV TABLE OF CONTENTS ................................................................................................. VI LIST OF TABLES ........................................................................................................... IX LIST OF FIGURES ......................................................................................................... XI ABBREVIATION .......................................................................................................... XII 1 INTRODUCTION ...................................................................................................... 1 1.1 Background of the study ...................................................................................... 1 1.2 Features of typical FSS ........................................................................................ 4 1.3 Problem statement ............................................................................................. 14 1.3.1 Ideal vs actual use of FSS .......................................................................... 15 1.3.2 Debiasing ................................................................................................... 18 1.4 Research objectives ........................................................................................... 21 1.5 Significance of the study ................................................................................... 26 1.5.1 Theoretical contribution ............................................................................