The Tourism Forecasting Competition

By George Athanasopoulos, Haiyan Song, Rob J Hyndman, Konstantinos Nikolopoulos, D. Wu, Nikolaos Bougioukos. 2011

314 citations recorded by the source corpus.

The performance of numerous methods for forecasting tourism demand is evaluated. A wide range of forecasting methods are implemented. Some of these methods are used widely in the tourism forecasting literature and some are new.

Subfields: Economics and Econometrics, Management Science and Operations Research, Tourism, Leisure and Hospitality Management, Evaluation & Benchmarks, Time-Series & Forecasting

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Management Science and Operations Research

In Tourism, Leisure and Hospitality Management

In Evaluation & Benchmarks

In Time-Series & Forecasting

Citations in the corpus

N-BEATS: Neural basis expansion analysis for interpretable time series forecasting (2019, methodology): “The following metrics are commonly used to evaluate forecasting performance (Hyndman & Koehler, 2006; Makridakis & Hibon, 2000; Makridakis et al., 2018b; Athanasopoulos et al., 2011):”
Forecasting: theory and practice (2020, background): “The tourism forecasting competition (Athanasopoulos et al., 2011) also showed that exogenous variables do not add value, while naive forecasts perform very well on a yearly frequency.”
Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions (2019, unknown): “The other two datasets that we select for the experiments are both taken from Kaggle challenges, the Web Traffic Time Series Forecasting Competition for Wikipedia articles and the Tourism Dataset Competition (Google, 2017; Athanasopoulos et al., 2010). The task of the first competition is to predict”
Improving forecasting by estimating time series structural components across multiple frequencies (2014, methodology): “There are two types of aggregation in the forecasting literature (Babai et al., 2012). On the one hand, temporal aggregation refers to time (nonoverlapping) aggregation for a specific time series. This converts a high frequency time series into a lower frequency time-series, according to the selecte”
Making and Evaluating Point Forecasts (2009, methodology): “…arise, such as the comparability of scores across time series with realizations of differing magnitude and volatility, and commonly used evaluation methods remain controversial (Armstrong and Collopy 1992; Fildes 1992; Ahlburg et al. 1992; Hyndman and Koehler 2006; Athanasopoulos et al. 2011).”
Deep State Space Models for Time Series Forecasting (2018, background): “This includes monthly and quarterly time series from the tourism competition dataset [2] describing tourism demand, hourly time series from the M4 competition [20] and parts dataset [6] which contains monthly demand of spare parts at a US auto-mobile company.”
'Horses for Courses' in demand forecasting (2014, background): “Lastly, Athanasopoulos et al. (2011) found that tourism data are best extrapolated using time series approaches rather than causal models, whilst the forecasting performance of “Naive” for annual data was “hard to beat”.”