پیش بینی تقاضای گردشگری خارجی (یک مطالعه موردی برای ایران) (مقاله علمی وزارت علوم)
درجه علمی: نشریه علمی (وزارت علوم)
آرشیو
چکیده
پیش بینی جریان آینده ی گردشگری ورودی برای تعیین مخارج سرمایه گذاری در صنعت گردشگری، هم برای بخش دولتی و هم برای بخش خصوصی، ضروری است. برای بخش دولتی و عمومی تخمین تقاضای گردشگری به منظور استفاده ی کارا از صنعت حمل ونقل و برنامه ریزی در نحوه ی تخصیص منابع حیاتی است. همچنین پیش بینی صحیح می تواند برای بخش خصوصی مانند شرکت های حمل ونقل هوایی در برنامه ریزی و طرح ریزی خطوط هوایی، تجهیزات، امکانات رفاهی و برنامه ریزی برای منابع انسانی مفید باشد. علی رغم اهمیت این موضوع در حوزه ی گردشگری، مطالعات انجام شده ی کشور ما در این حوزه بسیار محدود است. از سوی دیگر، ازآنجایی که اثبات شده است مدل تک متغیره روش بسیار موفقیت آمیزی برای پیش بینی سری زمانی گردشگری است، در این مطالعه با استفاده از داده های ماهانه ی گمرک جمهوری اسلامی ایران در فاصله ی فروردین 1378 تا اسفند 1390، مدل های تک متغیره ی ARFIMA، روش هوشمند ANN و مدل ARFIMA-ANN را که آلاداگو همکاران در سال 2012 پیشنهاد کرده اند، برای سری زمانی گردشگری کشور برآورد کردیم و نتایج حاصل از پیش بینی آن ها را با یکدیگر مقایسه نموده ایم. استفاده از معیارهای RMSE,MAPE,MAE برای ارزیابی صحت پیش بینی افق های زمانی متفاوت در میان مدل های مذکور نشان می دهد که مدل ARFIMA-ANN در افق های زمانی 6،12، 18 و 24 ماه پیش رو توان بالاتری در پیش بینی نسبت به مدل های رقیب دارد و می تواند به عنوان مدلی مناسب برای برآورد و پیش بینی سری زمانی گردشگری کشور مورد استفاده قرار گیرد.Forecasting International Tourist (A Case Study of Iran)
Extended
Forecasting is an essential analytical tool for tourism policy and planning. Business success, marketing decisions, government’s investment policy as well as macroeconomic policy are influenced by the accuracy of tourism forecasts, since the tourism product comprises a number of services that cannot be accumulated, Accurate forecasts of tourism demand are paramount to ensure the availability of such services when demanded. on the other hand since univariate time series modeling has proved to be a very successful method for forecasting tourist arrivals, In this article, along with study of ARFIMA and artificial intelligence methods ,we use the new hybrid approach combining ARFIMA and feed forward neural networks (FNN) proposed by Aladagh et al. in 2012.For this purpose, ARFIMA, ANN and ARFIMA-ANN models are considered and compared their results in different time horizon using IRICA(The Islamic Republic of Iran Customs Administration) monthly time series of tourist arrivals to Iran from march 1999 to march 2012. According to MAPE, RMSE and MAE criteria, the forecasting performance of the ARFIMA-ANN model is better than the ARFIMA and ANN models at the horizons of 6, 12, 18 and 24 months and thus it can be used as suitable model for forecasting tourist arrivals to Iran.
Introduction
Forecasting is an essential analytical tool for tourism policy and planning. Accurate forecasting of future tourist flow is essential to determine successful investments in the tourism industry for both the public and the private sectors. For the public sector, estimation of tourism demand is important in order to make efficient use of transportation and resources. For the private sector, such as airlines, good tourism forecasting is useful for planning aircraft, facilities and manpower needs (Chang and Liao, 2010:215), despite of the importance of this issue, very little research has been done in this area in IRAN. Therefore In this article, ARFIMA, ANN and ARFIMA-ANN models were used for forecasting of country’s tourism time series.
Materials and Methods
Since univariate time series modeling has proved to be a very successful method for forecasting tourist arrivals, it is also the method employed in this paper. In order to choose best model for forecasting tourist arrivals to Iran ARFIMA, ANN and ARFIMA-ANN methods were compared to forecast tourist flows to Iran at the horizons of 6, 12, 18 and 24 months using IRICA(The Islamic Republic of Iran Customs Administration) monthly time series of tourist arrivals to Iran from march 1999 to march 2012.
Discussion and Results
According to MAPE, RMSE and MAE criteria, the best results is obtained by hybrid(ARFIMA-ANN) method which means that ARFIMA-ANN thus it can be used as suitable model for forecasting tourist arrivals to Iran.
Conclusions
The ARFIMA-ANN method is appropriate method to forecast foreign tourist to Iran and it will can be used as suitable model for forecasting tourist arrivals to Iran.
References:
Abrishami, H. and Mehrara, M. (2002). Applied econometrics (New approach), Tehran: University of Tehran Press. (In Persian)
Aladag, C.H., Egrioglu, E. and Kadilar, C. (2012). Improvement in forecasting accuracy using the hybrid model of ARFIMA and feed forward neural network, American Journal of Intelligent Systems, 2(2):12-17.
Archer, B.H. (1987). Demand forecasting and estimation, In Ritchie, J.R.B. and Goeldner, C.R. (Eds) Travel, tourism and hospitality research, New York: Wiley.
Aslanargun, A., Mammadov, M., Yazici, B. and Yolacan, S. (2007). Comparison of ARIMA, neural networks and hybrid models in time series: Tourist arrival forecasting, Journal of Statistical Computation and Simulation, 77: 29–53.
Athanasopoulos, G., Hyndman, R.J., Song, H. and Wu, D.C. (2011). The tourism forecasting competition, International Journal ofForecasting, 27: 822–844.
Burger, C.J.S.C., Dohnal, M., Kathrada, M. and Law, R. (2001). A practitioners guide to time-series methods for tourism demand forecasting–A case study of Durban, South Africa, Tourism Management, 22: 403–409.
Claveria, O., Monte, E. and Torra, S. (2014). Tourism demand forecasting with neural networkmodels: Different ways of treating information, International Journal of Tourism Research, 1-20, DOI: 10.1002/jtr.2016.
Claveria, O. and Torra, S. (2014). Forecasting tourism demand to Catalonia: Neural networks vs. time series models, Economic Modelling, 36: 220-228.
Chang, Y.W. and Liao, M.Y. (2010). A seasonal ARIMA model of tourism forecasting: The case of Taiwan, Asia Pacific journal of Tourism research, 15(2): 215-221.
10. Chu, F.L. (2008). A fractionally integrated autoregressive moving average approach to forecasting tourism demand, Tourism Management, 29: 79-88.
11. Chu, F.L. (2009). Forecasting tourism demand with ARMA-based methods, Tourism Management, 30:741-751.
12. Cuhadar, M. (2014). Modelling and forecasting inbound tourism demand to Istanbul–A comparative analysis, European Journal of Business and Social Sciences, 2:12.
13. Doornik, A. and Ooms, M. (1999). A package for estimating, forecasting and simulating ARIFMA models: Help of ARIFMA package 1.0 for Ox, from fmwww.bc.edu/ec-p/software/ox/Ox.arfima.v2.1.pdf.
14. Gil-Alana, L.A. (2005). Modeling international monthly arrivals using seasonal univariate long-memory processes, Tourism Management, 26: 867-878.
15. Granger C.W.J and Joyeux, R. (1980). An introduction to long-memory time series models and fractional differencing- J, Time Series Anal, 1(1):15-29.
16. Hwang, K.P. and Day, Y.J. (2013). Tourism revenue forcasting: A hybrid model approach, Actual Problems of Economics, 141(3): 478-484.
17. Kuan-Yu, C. (2011). Combining linear and nonlinear model in forecasting tourism demand, Expert Systems with Applications, 38: 10368–10376.
18. Lewis, C.D. (1982). International and business forecasting methods, London: Butterworths.
19. Lildhold, P. (2000). Long memory an ARFIMA modeling, University of Aarhus.
20. Loganathan, N. and Ibrahim, Y. (2010). Forecasting international tourism demand in Malaysia using Box Jenkins sarima application, South Asian Journal of Tourism and Heritage, 3(2): 50-59.
21. Saayman, A. and Saayman, M. (2010). Forecasting tourist arrivals in South Africa, Acta Commercii, 10: 281-293.
22. Shitan, M. (2008). Time series modelling of tourist arrivals to Malaysia, InterStat, (October): 1-12.
23. Song, H. and Li, G. (2008). Tourism demand modelling and forecasting–A review of recent research, Tourism Management, 29 (2): 203-220.
24. Song, H. and Witt, S.F. (2006). Forecasting international tourist flows to Macau, Tourism Management, 27: 214-224.
25. Teixeira, J. P. and Fernandes, P.O. (2012). Tourism time series forecast-different ANN architectures with time index input, Procedia Technology, 5: 445-454.
26. Tseng, F.M., Yu, H.C. and Tzeng, G.H. (2002). Combining neural network with seasonal time series ARIMA model, Technological Forecasting and Social Change, 69(1):71–87.
27. UNWTO. (2012). ‘Why tourism?’ [Online article]. Available from: http: // www2.unwto.org/en/ content/why- tourism, [Accessed 15 September 2012].
28. Xiu, J. and Jin, Y. (2007). Empirical study of ARFIMA model based on fractional differencing, Physica A, 377:138 –154.
29. Zhang, G.P. (2003). Time series forecasting using a hybrid ARIMA and neural network model, Neurocomputing, 50: 159-175.
30. Zhang, G.P., Patuwo, E.B. and Hu, M.Y. (1998). Forecasting with artificial neural networks: the state of the art, International Journal of Forecasting, 14: 35–62.
31. Zhang, G.P., Patuwo, E.B. and Hu M.Y. (2001). A simulation study of artificial neural networks for nonlineartime-series forecasting, Computer & Operation Research, 28: 381–396.
تبلیغات
