Advanced Computational Approaches for Predicting Tourist Arrivals: the Case of Charter Air-Travel

Tourism is one of the major industries profiting various sectors of the economy, such as the transportation, accommodation, entertainment and so on. According to the World Tourism Organization (2008), international tourism grew at around 5% during the first four months of the year 2008. Fastest growth was observed in the Middle East, North-East and South Asia, and Central and South America. Even though, uncertainty over the global economic situation is affecting consumer confidence and could hurt tourism demand, for 2008 as a whole, UNWTO maintains a cautiously positive forecast. Moreover, international trends show that tourists are becoming more discerning in their choice of destinations and, therefore, becoming less predictable and more spontaneous in terms of their consumption patterns (Burger et al. 2001). Air transportation is probably the most important mode for international travel and leisure. A typical characteristic of air tourism in Europe is the extensive use of nonscheduled/charter flights and the existence of low-cost carriers in the leisure travel market, that account for 8% of passengers and 3% or revenues in the aviation industry (Dresner 2006). Non-scheduled demand is typical in Mediterranean countries where connections are essentially touristic and characterized by non-scheduled services. In this type of air travel, the ability to accurately predict tourist arrivals is of importance in the successful management and operation of the airport facilities, as well as the adjacent transportation network. Yet, the literature has little to offer in modeling demand stemming from non-scheduled flights, as such series exhibit seasonality, intense variability and inherent unpredictability. This paper develops and tests advanced computational approaches in order to predict nonscheduled/charter international tourist demand. The computational challenges that may arise in such a problem are twofold: first, to treat seasonal and stochastic characteristics of non-scheduled tourist demand, and, second, to develop models that consider past tourist demand characterists. This paper focuses on developing ARFIMA models that consider both non-stationarity and long-term memory effects in the auto-regressive process and temporal neural networks with advance genetically optimized characteristics that treat both nonlinearity and non-stationarity.

[1]  A. Graham.  Have the major forces driving leisure airline traffic changed , 2006 .

[2]  Jaesoo Kim,et al.  Segmenting the market of West Australian senior tourists using an artificial neural network , 2003 .

[3]  Rob Law,et al.  A neural network model to forecast Japanese demand for travel to Hong Kong , 1999 .

[4]  Martin Dresner,et al.  Leisure versus business passengers: Similarities, differences, and implications , 2006 .

[5]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[6]  Rob Law,et al.  A practitioners guide to time-series methods for tourism demand forecasting - a case study of Durban, South Africa , 2001 .

[7]  Mitsuo Gen,et al.  Genetic algorithms and engineering optimization , 1999 .

[8]  Rob Law,et al.  Data Mining in Tourism Demand Analysis: A Retrospective Analysis , 2007, ADMA.

[9]  Nigel Dennis.  Can the European low-cost airline boom continue?: Implications for regional airports , 2004 .

[10]  R. Neufville.  MANAGEMENT OF MULTI-AIRPORT SYSTEMS: A DEVELOPMENT STRATEGY , 1995 .

[11]  S. Washington,et al.  Statistical and Econometric Methods for Transportation Data Analysis , 2010 .

[12]  Richard T. Baillie,et al.  Further Long Memory Properties of Inflationary Shocks , 2002 .

[13]  C. Granger,et al.  AN INTRODUCTION TO LONG‐MEMORY TIME SERIES MODELS AND FRACTIONAL DIFFERENCING , 1980 .

[14]  Melanie Mitchell,et al.  An introduction to genetic algorithms , 1996 .

[15]  S. Barrett,et al.  Airport competition in the deregulated European aviation market , 2000 .

[16]  R. Law.  Back-propagation learning in improving the accuracy of neural network-based tourism demand forecasting , 2000 .

[17]  Eleni I. Vlahogianni,et al.  Optimized and meta-optimized neural networks for short-term traffic flow prediction: A genetic approach , 2005 .

[18]  Philippe A. Bonnefoy,et al.  EMERGENCE AND IMPACT OF SECONDARY AIRPORTS IN THE UNITED STATES , 2004 .

[19]  P J Webros.  BACKPROPAGATION THROUGH TIME: WHAT IT DOES AND HOW TO DO IT , 1990 .

[20]  Matthew G. Karlaftis,et al.  DEMAND CHARACTERISTICS FOR CHARTER AIR-TRAVEL , 1998 .

[21]  Berna Yazici,et al.  Comparison of ARIMA, neural networks and hybrid models in time series: tourist arrival forecasting , 2007 .

[22]  V. Cho.  A comparison of three different approaches to tourist arrival forecasting , 2003 .