بخش های بازار بر اساس الگوهای حرکتی غالب گردشگران

This paper presents an innovative method for tourist market segmentation-based on dominant movement patterns of tourists; that is, the travel sequences or patterns used by tourists most frequently. There were three steps to achieve this goal. In the first step, general log-linear models were adopted to identify the dominant movement patterns, while the second step was to discover the characteristics of the groups of tourists who travelled with these patterns. The Expectation–Maximisation algorithm was then used to partition tourist segments in terms of socio-demographic and travel behavioural variables. The third step was to select target markets based upon the earlier analysis. These methods were applied to a sample of tourists, over the period of a week, on Phillip Island, Victoria, Australia. A significant outcome of this research is that it will assist tourism organisations to identify tourism market segments and develop better tour packages and more efficient marketing strategies aligned to the characteristics of the tourists.

The movement of tourists is a complex process which can be modelled at a micro level as a continuous process with high resolution, such as in centimetres or at a macro level as discrete processes with low resolution, such as kilometres from one area to another. Tourist movement patterns are a theme of recurring or repeat movement sequences. This paper focuses on movement patterns at the macro level. Movement patterns represent the sequence of movements by tourists from one-attraction site to another. The dominant movement patterns are the sequences or patterns that are used by tourists most frequently. These tourist movement patterns are vital to park managers or tour operators to understand the location of popular sites and the timing of visits. More importantly, an understanding of movement patterns can indicate how tourists combine attractions together and arrange their schedules. Traditionally, tourism market segmentation is conducted to identify groups of tourists from an origin perspective, for example, analysis of the origin of tourists from China or Australia. Alternatively, analysis can be performed from a destination perspective, where the tourism market is segmentation-based on a single destination such as Melbourne. However, tourists usually visit several attractions during a trip. To understand the spatial combination of attractions and to clarify the characteristics of tourists who travel to these attractions will assist tourist organisations to design more appropriate and profitable tour packages. The aim of this study was to develop a methodology to identify the characteristics of tourists who travel with dominant movement patterns. The first step involved identification of the dominant movement patterns based on the analysis of categorical data using general log-linear models. In the second step, the Expectation–Maximisation (EM) algorithm used in a mixture model framework was adopted to identify the characteristics of tourists who travel with dominant movement patterns. Tourists were divided into different segments based on similar socio-demographic characteristics and travel modes such as type of travel group, modes of transport or visit frequency. For example, the tourists in segment 1 who travel with pattern A may mostly be females travelling with their family by car. Finally, appropriate target markets can be determined from the socio-demographic data. Sections 2 and 3 of this paper address the first two steps, followed by a case study of tourists visiting Phillip Island Nature Park in Victoria, Australia.

This paper presents a novel method to segment tourist markets associated with dominant movement patterns of tourists. Log-linear models were used to identify dominant movement patterns of tourists. Tourists who travelled with the same dominant movement pattern, were then divided into different segments using the EM algorithm based on the geographic, socio-demographic and trip-related behavioural variables. This method was specifically applied to develop tour packages for Phillip Island Nature Park. The survey was conducted at the four major attractions at the Phillip Island Nature Park Tourists visiting the island who did not visit these attractions were not surveyed. However, the Park managers estimate that these would comprise less than 10% of tourists visiting the island and therefore it is unlikely that significant movement patterns were missed by the survey. Log-linear models tested the significance of movement patterns and provided the threshold for dominant patterns using a p-value at the level of 0.05.The dominant movement patterns could be used to develop tour package, assist park managers in deciding how long to open an attraction and how the daily program of activities should be arranged for an attraction. One important issue for utilisation of log-linear models is sample size. The case study shows that if zero is recorded too often as the frequency of movement patterns, the expected frequencies of movement patterns will converge to zero during iterative fitting. Therefore, a large sample size is necessary ( Kennedy, 1992). Small sample size is the major limitation of this case study. Ideally, the EM algorithm would be used to find market segments for each significant movement pattern. However, this could not be done using the Phillip Island data because of the small sample numbers of tourists travelling with each of the patterns. Instead, we have used the EM algorithm to find market segments using all of the available tourist data and then applied it to identify market segments for the movement patterns with sufficient data. This approach provides insight that may be used to assist the development of tour packages for Phillip Island, but with more available data the results may be improved and of greater detail. Witten and Frank (2000) suggest that a supervised model, namely, the classification method, could be used to analyse the results of the EM algorithm. However, expert experience or knowledge is sometimes needed to identify the characteristics of tourism market segments based on the results of the EM algorithm. The large number of daily monetary transactions (purchases) in the Phillip Island Nature Park suggests that in future the methods described here could be applied to tourist monetary transaction data. The tourist transaction data can record tourist ID numbers, the ID numbers of attractions that tourists visited, the dates of the transaction, and in-store tourist information such as tourist profiles. Therefore, based on these transaction records, tourist movement patterns could be identified and further market segments identified. However, this method is only suitable for developed attractions with their own information centre and EFTPOS (Electronic Funds Transfer at the Point of Sale) machines. Of course, the privacy issues regarding the use of transaction data also need to be considered.