What is the tourism decision-making model?

They are structural model, simulation model, qualitative model and gravity model.

Tourism demand forecast

1. Concentration of spatio-temporal distribution of tourism demand

One notable feature of tourism demand is that it changes with time. Another feature is that Every tourist destination has its own relatively stable source of tourists. Quantitatively studying and measuring the changes in tourism demand over time and the spatial distribution changes in tourist source areas are of great help to tourism planning and business decision-making.

1>Time distribution concentration of tourism demand

Seasonal (time) intensity index: The time distribution concentration of tourism demand is caused by the seasonality of tourism and can be used Seasonal (time) intensity index for quantitative analysis.

In the formula: R is the time distribution intensity index of tourism demand

xi is the proportion of tourists in each month to the whole year

The closer the R value is to zero , the more even the time distribution of tourism demand is; the greater the R value, the greater the time change, and the greater the difference between low and peak tourism seasons. The R value is affected by changes in tourism demand and the length of the selected period, so it is suitable for comparisons between different years (periods) and comparisons between different tourist destinations (facilities).

Peak index: used to measure the tendency of tourists to use tourist facilities to visit a tourist destination in a certain period compared to other periods. The calculation formula is

where: Pn is the peak index;

V1 is the number of tourists in the busiest period;

Vn is the number of tourists in the nth period Number of tourists

n is the reference period (1 = the busiest period)

The value of Pn not only depends on the peak level, but also depends on the total number of tourists and the selected period. Therefore, a major use of the index is to compare tourist destinations or to examine peak trends in a facility over time. When the number of tourists is the same in all periods, Pn=0; when the number of tourists is concentrated in certain periods, the Pn value will increase. The value of n, that is, the period used for comparison with the busiest period, is to a large extent the result of selection, which depends on the available data, the purpose of the study and the research experience.

2>Spatial distribution concentration of tourism demand

The spatial distribution structure of tourism demand mainly refers to the geographical origin and intensity of tourists. Its concentration can be quantitatively analyzed using the geographical concentration index . The formula is:

In the formula: G is the geographical concentration index of the tourist source place

Xi is the number of tourists in the th tourist source place

T is tourism The total number of tourists received by a place

n is the total number of tourist source places

The fewer the tourist sources, the more concentrated they are, and the G value is closer to 100; the smaller the G value, the more tourist source places the dispersion. For a tourist destination, the more dispersed the tourist source areas are, the more stable the tourism operation will be.

2. Trend extrapolation model

The trend extrapolation model is based on the event data that has already occurred and predicts possible future situations based on a series of historical data. No matter which type of trend extrapolation model, there is the same assumption: the trend of historical data will continue for a period of time in the future. Trend extrapolation models mainly include regression models and time series models.

1>Regression analysis method

The linear regression model is the simplest and most commonly used trend extrapolation mathematical model, which is often used to change tourism demand in annual time units. . The form is:

y=a+bx

In the formula: y is the dependent variable, x is the independent variable, a is the constant term; b is the regression coefficient of y on x. For the specific operation of this model, please refer to the relevant content of "Common Statistical Methods".

Bao Jigang (1989) established a linear regression equation for the number of visitors to Beijing’s Xiangshan Park through research:

y=-35047.0088+17.859x

r＝0.9828

In the formula: y is the annual tourist volume (10,000 people)

x is the year

r is the correlation coefficient

We know that the number of tourists from 1979 to 1985 were 291.58, 318.75, 326.97, 361.92, 359.73, 381.63, and 405.09 respectively; we can use the model to get the predicted value in 1986 to be 420.97.

(See "Tourism Geography" for details)

2>Time series model

The time series model is mainly used to predict fluctuating tourism demand, such as those that are significantly affected by seasonality. This model can be used to predict demand for destinations.

In time series analysis, the forecasting process must first obtain a statistical fitting curve through historical data of past demand, and then extend this fitting curve forward to estimate demand in future periods. quantity. Such fitting curves can generally be divided into three categories: horizontal demand curves, trend demand curves and seasonal demand curves.

Commonly used horizontal time series models include the linear moving average model and the linear exponential smoothing model.

Commonly used trend demand models include linear trend models, including linear regression models, quadratic moving average models, etc.; non-linear trend models, such as quadratic regression models and cubic exponential smoothing models.

Commonly used seasonal demand models include seasonal level models, seasonal cross-trend models, etc.

3. Gravity model

The gravity model is the most widely used model in urban and regional economic research. In the late 20th century, some foreign scholars took the lead in applying this model to tourism research for tourist prediction, tourism attraction determination, and tourism planning.

In 1966, Crampon L J first used the gravity model in tourism research. The gravity model he established is also the basic gravity model used by other researchers:

Where: Tij is the tourist source Some measure of the number of trips between place i and destination j

Pi is some measure of the population size, wealth or travel tendency of source place i

Aj is destination j Some measure of attractiveness or capacity

Dij is the distance between source i and destination j

G, b is an empirical parameter

The source population can be the population of a specific area such as a city, or the number of people who will travel in the future. It can be a combination of several variables.

Destination attractiveness can be a combination of several variables such as aesthetic appeal, resource capacity, and popularity of tourist destinations.

Distance generally refers to perceived distance, which can be expressed in terms of actual distance or travel time.

Later, some scholars proposed some modified models mainly for the distance variable in response to some shortcomings in this model. I will not introduce them one by one here.

4. Delphi method

The Delphi method is one of the most famous and controversial methods in forecasting models. When historical information or data is insufficient, or when a considerable degree of subjective judgment is required in the model, the Delphi method needs to be used to predict the future trend of events. At present, the Delphi method has been widely used in the field of soft science and has achieved many satisfactory results. The key to determining the success of the Delphi method lies in the design of the questionnaire and the qualifications of the selected experts.

Prediction using the Delphi method generally includes the following work steps:

1>Determine the prediction problem and select the expert group to consult

Expert selection of the expert group It must be comprehensive and representative to ensure that the prediction is comprehensive and comprehensive. The number of experts is determined by the complexity of the problem. Usually 40 to 50 people.

2>Develop and distribute the first round of questionnaires

The questionnaires are filled in completely independently by experts, that is, there is no communication between experts in any form to avoid mutual interference and influence. The first round of questionnaires included two parts: one was to give an overview of the research projects being conducted to the experts, and the other was to ask the experts to identify the probability and possible time of possible future events.

3>Collect the first round of questionnaires and organize the results

The process includes the calculation of the median, indicating the range of the two middle four scores, that is, both sides of the median contain 50% of the total prediction range of numbers.

4>The second round of questionnaires

Attach the statistical summary of the first round of questionnaires to the second round of questionnaires and send it to the expert group for the first round of consultation. Each expert will first A copy of the answer sheet for the round is also attached for reference. Ask each expert if he or she wants to change his prediction after seeing the group's average results. If the expert's prediction is not within the two middle quartiles and he is unwilling to change his original prediction, ask the expert to give a reason.

5>Recycle the second round of questionnaires and organize the results

Including new prediction results and the opinions of some experts who disagree with the results of the first round of questionnaires.

6>The third round of questionnaires

The results and opinions of the second round of questionnaires will be integrated into the third round. The instructions for the questionnaire are similar to those of the second round. The main difference is the addition of opinions from some experts who predict different outcomes.

After the results of the third round of questionnaires come out, it is necessary to decide whether a fourth round of questionnaires is needed to obtain further predictions. If the vast majority of predictions are already near the median after two surveys, there is no need to conduct the next round of surveys.