• • 上一篇    

考虑节假日影响效应的景区客流量预测研究——基于Prophet-NNAR的混合预测方法

李勇, 李云鹏   

  1. 首都经济贸易大学工商管理学院, 北京 100070
  • 收稿日期:2021-10-03 修回日期:2022-03-15 发布日期:2022-07-29
  • 通讯作者: 李云鹏,Email:liyunpeng@cueb.edu.cn.
  • 基金资助:
    北京市自然科学基金面上项目(9222005)资助课题.

李勇, 李云鹏. 考虑节假日影响效应的景区客流量预测研究——基于Prophet-NNAR的混合预测方法[J]. 系统科学与数学, 2022, 42(6): 1537-1550.

LI Yong, LI Yunpeng. Research on the Tourist Volume Forecast of Scenic Spots Considering the Effect of Holidays-A Hybrid Prediction Method Based on Prophet-NNAR[J]. Journal of Systems Science and Mathematical Sciences, 2022, 42(6): 1537-1550.

Research on the Tourist Volume Forecast of Scenic Spots Considering the Effect of Holidays-A Hybrid Prediction Method Based on Prophet-NNAR

LI Yong, LI Yunpeng   

  1. School of Business Administration, Capital University of Economics and Business, Beijing 100070
  • Received:2021-10-03 Revised:2022-03-15 Published:2022-07-29
近年来,旅游景区因超负荷接待造成游客滞留的事件屡见不鲜,如何准确有效地预测景区客流量、合理调配资源成为眼下景区管理者十分关切的问题.由于节假日等外部因素的影响,景区客流量的时间序列曲线通常呈现非线性的特征,这增加了准确预测旅游客流量的难度.文章提出一种考虑节假日影响效应的景区客流量预测方法,即Prophet-NNAR混合预测方法:首先,基于考虑了节假日影响因素的Prophet模型预测原始景区客流量序列;其次,使用神经网络自回归模型(NNAR)对Prophet模型预测值的残差部分进行预测;最后,将二者相加作为Prophet-NNAR混合模型的最终预测结果.文章以2013年1月1日至2017年7月31日的九寨沟景区历史客流量数据为研究样本,使用R软件验证Prophet-NNAR混合预测方法的有效性,研究发现Prophet-NNAR混合预测方法的预测性能除了优于单一的模型方法(Prophet模型、不考虑节假日效应Prophet模型、NNAR模型)外,还强于季节自回归求和滑动平均(SARIMA)、指数平滑模型(ETS).此外,借助Diebold-Mariano检验进一步确定了Prophet-NNAR模型的优异性.
Recently, incidents of tourists being stranded due to the overloaded reception of tourists in attractions are very common. Therefore, accurate and effective prediction of the tourist volume in attractions and rational allocation of resources has become a challenge for scenic spot managers. Because of the influence of external factors, such as holidays, the time series curve of tourist volume in attractions usually presents nonlinear characteristics, which undoubtedly increases the practical difficulty of accurately predicting the tourist volume. This study proposes a method for forecasting tourist volume in attractions that considers the effects of holidays, namely, the Prophet-neural network autoregressive (NNAR) hybrid forecasting method. First, the Prophet model, which considers the effects of holidays, is used to predict the original tourist volume of attractions. Then, the NNAR model is used to predict the residual part of the predicted value of the Prophet model. Finally, the two results are combined as the final prediction result of the Prophet-NNAR hybrid model. Taking the historical tourist volume data of Jiuzhaigou scenic spot (from January 1, 2013 to July 31, 2017) as the data source, the effectiveness of the Prophet-NNAR hybrid forecasting method is verified using the R software. Results show that the Prophet-NNAR hybrid forecasting method is effective. The prediction performance of the Prophet-NNAR hybrid forecasting method is not only better than that of single-model methods (i.e., Prophet model, Prophet model that does not consider the effects of holidays, and NNAR model) but also stronger than the seasonal autoregressive integrated moving average and exponential smoothing models. Moreover, the combined results of the Diebold-Mariano test can confirm that the superiority of the Prophet-NNAR hybrid forecasting method over the other methods is statistically significant.

MR(2010)主题分类: 

()
[1] Song H.Tourism forecasting:An introduction.International Journal of Forecasting, 2011, 27(3):817-821.
[2] Bi J W, Liu Y, Li H.Daily tourism volume forecasting for tourist attractions.Annals of Tourism Research, 2020, 83:102923.
[3] Sun S, Wei Y, Tsui K L, et al.Forecasting tourist arrivals with machine learning and internet search index.Tourism Management, 2019, 70:1-10.
[4] Lu H, Zhang J, Xu Z, et al.Prediction of tourist flow based on multi-source traffic data in scenic spot.Transactions in GIS, 2021, 25(2):1082-1103.
[5] García Rodríguez Ó.Forecasting tourism arrivals with an online search engine data:A study of the Balearic Islands.Pasos Revista De Turismo Y Patrimonio Cultural, 2017, 15(4):943-958.
[6] Lin S J, Chen J Y, Liao Z X.An EMD-BP integrated model to forecast tourist number and applied to Jiuzhaigou.Journal of Intelligent&Fuzzy Systems, 2018, 34(2):1045-1052.
[7] Ongan S, Gozgor G.Tourism demand analysis:The impact of the economic policy uncertainty on the arrival of Japanese tourists to the USA.International Journal of Tourism Research, 2018, 20(3):308-316.
[8] Liu Y Y, Tseng F M, Tseng Y H.Big Data analytics for forecasting tourism destination arrivals with the applied vector autoregression model.Technological Forecasting and Social Change, 2018, 130:123-134.
[9] Zhang B, Li N, Shi F, et al.A deep learning approach for daily tourist flow forecasting with consumer search data.Asia Pacific Journal of Tourism Research, 2020, 25(3):323-339.
[10] Clark M, Wilkins E J, Dagan D T, et al.Bringing forecasting into the future:Using Google to predict visitation in U.S.national parks.Journal of Environmental Management, 2019, 243:88-94.
[11] Fronzetti Colladon A, Guardabascio B, Innarella R.Using social network and semantic analysis to analyze online travel forums and forecast tourism demand.Decision Support Systems, 2019, 123:113075.
[12] Song H, Li G.Tourism demand modelling and forecasting-A review of recent research.Tourism Management, 2008, 29(2):203-220.
[13] Song H, Qiu R T R, Park J.A review of research on tourism demand forecasting:Launching the Annals of Tourism Research Curated Collection on tourism demand forecasting.Annals of Tourism Research, 2019, 75:338-362.
[14] Yang X, Pan B, Evans J A, et al.Forecasting Chinese tourist volume with search engine data.Tourism Management, 2015, 46:386-397.
[15] 张婷婷,王沫然,魏得胜,等.季节调整FWA-SVR模型及其在旅游经济预测中的应用.系统科学与数学, 2021, 41(6):1572-1584.(Zhang T T, Wang M R, Wei D S, et al.Seasonally-Adjusted FWA-SVR model and its application in tourism economic forecast.Journal of Systems Science and Mathematical Sciences, 2021, 41(6):1572-1584.)
[16] 陆文星,戴一茹,李楚,等.基于改进PSO-BP神经网络的旅游客流量预测方法.系统科学与数学, 2020, 40(8):1407-1419.(Lu W X, Dai Y R, Li C, et al.Tourist traffic flow forecasting method based on improved PSO-BP neural network.Journal of Systems Science and Mathematical Sciences, 2020, 40(8):1407-1419.)
[17] Jiao E X, Chen J L.Tourism forecasting:A review of methodological developments over the last decade.Tourism Economics, 2019, 25(3):469-492.
[18] Wei X, Huang S (SAM), Yap G, et al.The influence of national holiday structure on domestic tourism expenditure:Evidence from China.Tourism Economics, 2018, 24(7):781-800.
[19] Liu H, Liu W, Wang Y.A study on the influencing factors of tourism demand from mainland China to Hong Kong.Journal of Hospitality and Tourism Research, 2021, 45(1):171-191.
[20] Otero-Giráldez M S, Álvarez-Díaz M, González-Gómez M.Estimating the long-run effects of socioeconomic and meteorological factors on the domestic tourism demand for Galicia (Spain).Tourism Management, 2012, 33(6):1301-1308.
[21] Song H, Li G, Witt S F, et al.Tourism demand modelling and forecasting:How should demand be measured?.Tourism Economics, 2010, 16(1):63-81.
[22] Chen R, Liang C Y, Hong W C, et al.Forecasting holiday daily tourist flow based on seasonal support vector regression with adaptive genetic algorithm.Applied Soft Computing, 2015, 26:435-443.
[23] Hyndman R J, Athanasopoulos G.Forecasting:Principles and Practice.OTexts, 2018.
[24] Taylor S J, Letham B.Forecasting at scale.The American Statistician, 2018, 72(1):37-45.
[25] Zhao N, Liu Y, Vanos J K, et al.Day-of-week and seasonal patterns of PM2.5 concentrations over the United States:Time-series analyses using the Prophet procedure.Atmospheric Environment, 2018, 192:116-127.
[26] Samal K K R, Babu K S, Das S K, et al.Time series based air pollution forecasting using SARIMA and prophet model.Proceedings of the 2019 International Conference on Information Technology and Computer Communications, 2019, 80-85.
[27] Li L, Zha Y, Zhang J, et al.Using Prophet forecasting model to characterize the temporal variations of historical and future surface urban heat island in China.Journal of Geophysical Research:Atmospheres, 2020, 125(23):e2019JD031968..
[28] Xie C, Wen H, Yang W, et al.Trend analysis and forecast of daily reported incidence of hand, foot and mouth disease in Hubei, China by Prophet model.Scientific Reports, 2021, 11(1):1445.
[29] Silva E S, Hassani H, Heravi S, et al.Forecasting tourism demand with denoised neural networks.Annals of Tourism Research, 2019, 74:134-154.
[30] Harvey A C, Peters S.Estimation procedures for structural time series models.Journal of Forecasting, 1990, 9(2):89-108.
[31] Maleki A, Nasseri S, Aminabad M S, et al.Comparison of ARIMA and NNAR models for forecasting water treatment plant's influent characteristics.KSCE Journal of Civil Engineering, 2018, 22(9):3233-3245.
[32] Yu G, Feng H, Feng S, et al.Forecasting hand-foot-and-mouth disease cases using wavelet-based SARIMA-NNAR hybrid model.Plos One, 2021, 16(2):e0246673.
[33] Liang Y H.Forecasting models for Taiwanese tourism demand after allowance for Mainland China tourists visiting Taiwan.Computers&Industrial Engineering, 2014, 74:111-119.
[1] 陆文星,戴一茹,李楚,李克卿. 基于改进PSO-BP神经网络的旅游客流量预测方法[J]. 系统科学与数学, 2020, 40(8): 1407-1419.
阅读次数
全文


摘要