High spatial and temporal detail in timely prediction of tourism demand

Abstract

What happens in forecasting problems when high frequency and high spatial detail data encounter significant publication delays? In this paper, we consider a monthly dynamic panel data model, augmented by Google Trends search query volume data, for tourism demand forecasting at high spatial detail, in which one of the main aspects is represented by a publication delay ranging from 8 to 15 months. Some findings in the tourism literature already specify forecasting/nowcasting applications considering a realistic time delay but not for more than 3 months.

Nowcasting tourist nights spent using innovative human mobility data

“…Often, such statistics are published months if not years after the fact. This is especially the case for statistics at higher spatial granularity [22]. This can limit the capacity of decision makers in both industry and the public sector to respond timely and adequately to ongoing trends.…”

“…For methods involving explanatory or predictor variables, web search data has become a recurrent choice [30,[34][35][36], even for forecasting at high spatial resolution such as municipalities [22], and sometimes in combination with economic (e.g. prices) data [37].…”

“…Often, such statistics are published months if not years after the fact, and as aggregated (areal) measures, under-mining the efficiency of the decision-making processes [21]. This is especially the case for statistics at higher spatial granularity [22]. For example, at the time of writing (August 2022), tourism demand statistics for European countries compiled by Eurostat such as the monthly number of nights spent or arrivals are available until April 2022 on a per country basis, and yet with some missing values.…”

Measuring tourism demand nowcasting performance using a monotonicity test

“…Governments and private firms are interested in accurate tourism demand forecasts, which are essential for effective planning and development of needed marketing and infrastructure (Song and Li, 2008). In the short run, the accurate nowcasting of tourism demand is also vital for enhancing business operations at mass or multiproduct tourism destinations (Emili et al, 2020) and monitoring the effectiveness of ongoing tourism-related policies (Castle et al, 2009; Jackman and Naitram, 2015).…”

Does the Destination Matter in Domestic Tourism?

“…One of the core challenges is choosing between highly substitutable destinations that offer similar experiences that can satisfy similar needs (Van Wee et al, 2019). Indeed, the more substitutable a destination may be, the more indifferent the tourist may be about where to go (Lo, 1991), especially at proximate destination (Emili et al, 2020). Substitutability is an especially critical issue in mature destinations (Brooker & Burgess, 2008) and places lacking clearly defined brand personalities (Pratt, 2013).…”