Accurate prediction of the tourism demand is important for tourism management. The state-of-art methods for predictive modeling used in tourism research include traditional statistical methods, soft computing methods, and artificial intelligence methods. Note that artificial intelligence methods, which were introduced to tourism research in the 1990s, have greatly improved the predictive accuracy of modeling methods. Machine learning is an important area of artificial intelligence, which has been widely recognized as a powerful tool for intelligent data analysis. BP neural network, as one of the traditional machine learning technique, has been widely used to construct predictive model for intelligent data analysis. However, BP neural network suffers from several drawbacks, such as overfitting, difficulties in setting parameters, and local minima problem, and hence the performance of BP neural network is very unstable in practical applications. This paper combines an advanced machine learning paradigm named ensemble learning with BP neural network to build neural network ensemble for tourism demand prediction. This study conducts predictive modeling for tourism demand of three important tourist source countries of US, Britain and Australia for travel to Chinese mainland. The results show that, by combining a number of diverse neural networks, neural network ensemble significantly improves the predictive accuracy over traditional statistical methods and traditional machine learning methods including single BP neural network. Such method provides a better choice for more accurate predictive modeling for tourism demand.
ZHANG Chen, ZHANG Jie
. Neural Network Ensemble for Chinese Inbound Tourism Demand Prediction[J]. SCIENTIA GEOGRAPHICA SINICA, 2011
, 31(10)
: 1208
-1212
.
DOI: 10.13249/j.cnki.sgs.2011.010.1208
[1] Tihomir S. A Comparison of Two Econometric Models (OLS And SUR) for Forecasting Croatian Tourism Arrivals [M]. Zagreb: Croatian National Bank, 2002:112-145.
[2] Carey G, Law R. Modeling and forecasting tourism demand for arrivals with stochastic nonstationary seasonality and intervention [J]. Tourism Management, 2002, 23(3): 499-510.
[3] Carey G, Law R. Incorporating the rough sets theory into travel demand analysis [J]. Tourism Management, 2003, 24(5): 511-517.
[4] Ao S I. Using fuzzy rules for prediction in tourist industry with uncertainty [J]. Computer Society, 2003: 213-218.
[5] Hernandez-Lopez, M. Future tourists' characteristics and decisions: The use of genetic algorithms as a forecasting method [J]. Tourism Economics, 2004, 10(3): 245-262.
[6] Law R. Back-propagation learning in improving the accuracy of neural network-based tourism demand forecasting [J]. Tourism Management, 2000, 21(4): 331-340.
[7] Mitchell T. Mahcine Leanring [M]. New York: McGraw-Hill, 1997:45-63.
[8] Mjolsness E, DeCoste D. Machine learning for science: State of the art and future prospects [J]. Science, 2001, 293(5537): 2051-2055.
[9] Jiang Y, Li M, Zhou Z-H. Generation of comprehensible hypothesis from gene expression data [M]// Li J, et al. Lecture Notes in Bioinformatics 3916. Berlin: Springer, 2006: 116-123.
[10] Li M, Zhou Z-H. Improve computer-aided diagnosis with machine learning techniques using undiagnosed samples [J]. IEEE Transactions on Systems, Man and Cybernetics-Part A: Systems and Humans, 2007, 37(6): 1088-1098.
[11] Law R. A neural network model to forecast Japanese demand for travel to Hong Kong [J]. Tourism Management, 1999, 20: 89-97.
[12] 雷可为, 陈 瑛. 基于BP神经网络和ARIMA组合模型的中国入境游客量预测[J]. 旅游学刊, 2007, 4(22): 20~25.
[13] Dietterich T G. Machine learning research: Four current diretions [J]. AI Magazine, 1997, 18(4): 97-136.
[14] Sollich P, Krogh A. Learning with ensembles: How over-fitting can be useful [M]//Touretzky D S, Mozer M C, Hasselmo M E. Advances in Neural Information Processing Systems 8. Cambridge, MA: The MIT Press, 1996: 190-196.
[15] Hansen L K, Salamon P. Neural network ensembles [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(10):993-1001.
[16] Freund Y, Schapire R E. Experiments with a new boosting algorithm [M]//Proceedings of the 13th International Conference on Machine Learning, 1996: 148-156.
[17] Breiman L. Bias, variance, and arcing classifiers [M]//Technical Report 460. Berkeley CA: Statistics Department, University of California, 1996.
[18] Friedman J, Hastie T, Tibshirani R. Additive logistic regression: A statistical view of boosting (with discussions) [J]. The Annals of Statistics, 2000, 28(2):337-407.
[19] Breiman L. Bagging predictors [J]. Machine Learning, 1996, 24(2):123-140.
[20] Bauer E, Kohavi R. An empirical comparison of voting classification algorithms: Bagging, boosting, and variants [J]. Machine Learning, 1999, 36(1-2):105-139.
[21] Breiman L. Random forest [J]. Machine Learning, 2001, 45(1):5-32.
[22] Efron B, Tibshirani R. An Introduction to the Boostrap [M].New York: Chapman & Hall, 1993:78-90.
[23] 中华人民共和国国家旅游局. 中国旅游统计年鉴 (1991~2009) [M].北京:中国旅游出版社.
[24] 中国国家统计局. 中国统计年鉴 (1991~2009)[M/OL]. http://www.stats.gov.cn/tjsj/ndsj/.
[25] 中国国家统计局. 国际统计年鉴 (1991~2009)[M/OL]. http://www.stats.gov.cn/tjsj/qtsj/gjsj/.
[26] Qu H-L, Lam S. A travel demand model for Mainland Chinese tourists to Hong Kong [J]. Tourism Management, 1997, 18(8):593-597.
[27] 张玉娟, 赵定涛.中国入境旅游需求影响因素分析[J]. 经济理论与经济管理, 2008, (5):51~55.
[28] Zinkevich M. Online convex programming and generalized infinitesimal gradient ascent [M]//Proceedings of 20th International Conference on Machine Learning, 2003: 928-936.
[29] Witten I H, Frank E. Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations [M]. San Francisco: Morgan Kaufmann, 2000:332-340.
