SARIMA와 딥러닝을 활용한 포스트 코로나 시대의 관광수요 예측
Forecasting International Tourist Visits in South Korea using SARIMA and RNN Models
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
많은 연구자들이 코로나-19 이 후의 관광수요를 예측하기 위해 다양한 연구를 진행하였지만, 딥러닝을 활용한 관광수요 예측은 문헌에서 부족한 실정이다. 본 연구는 고급 시계열 모형인 SARIMA 모형과 딥러닝 중 순환신경망(RNN) 모델을 활용하여 코로나 회복 시기의 대한민국의 관광수요를 예측한다. 본 연구는 두 가지 주요한 목적을 가진다. 첫째, SARIMA 모형과 순환신경망(RNN) 모형으로 코로나 시기의 관광수요를 예측해 보고, 두 모형을 비교한다. 둘째, 각각의 모형을 활용하여 코로나 기간의 관광산업 피해액을 추정하고, 회복 시기의 관광수요에 대한 시사점을 논의한다. SARIMA 모형의 경우, 코로나 시기의 입국자 인원수 감소를 51,483,170명으로 예측하였고, 이에 따른 피해액을 3년간 약 179조로 추정하였다. 반면, RNN 모형의 경우, 입국자 인원수 감소를 48,248,685명으로 예측하였고, 피해액을 3년간 약 167조로 추정하였다. SARIMA 모형의 경우 장기적으로 1,634,863명까지, RNN 모형의 경우 장기적으로 1,569,198명까지 대한민국 관광수요가 회복될 것으로 전망하고 있다. 본 연구는 빅데이터를 활용하여 딥러닝 기반의 수요 예측 모형을 구축하고 관광수요를 예측하였다는 데에 그 의의가 있다. 또한, 수요 예측 결과를 기반으로 관광학과 경영학 분야에서의 시사점을 논의하고자 한다.
Abstract
Many researchers have conducted various studies to predict tourism demand after COVID-19, but the number of studies using deep learning is insufficient in the literature. This study uses the SARIMA model, an advanced time series model, and the Recurrent Neural Network (RNN) model, one of deep learning techniques to predict tourism demand in South Korea during the COVID-19 recovery period. This study has two main purposes. First, we predict tourism demand during the COVID-19 recovery period with the SARIMA model and the RNN model, and compare the two models. Second, we would like to estimate the amount of damage in the tourism industry of South Korea during the COVID-19 period and discuss implications for tourism demand during the recovery period. In the case of the SARIMA model, the decrease in the number of inbound visits during the COVID-19 period was predicted to be 51,483,170, and the damage was estimated to be about 179 trillion over three years. On the other hand, in the case of the RNN model, the decrease in the number of inbound visits was predicted to be 48,248,685, and the damage was estimated to be about 167 trillion over three years. In the case of the SARIMA model, the demand for tourism in Korea is expected to recover to 1,634,863 in the long run and in the case of the RNN model, 1,569,198 in the long run. This research utilizes the deep learning algorithms using big data analyses and we believe our research makes significant methodological contributions to the tourism/marketing literature.
참고문헌 (30)
- 김도훈, "코로나19(COVID-19) 이후 방한 외래관광자 수요예측: 개입 ARIMA 분석 및 회복탄력성(resilience)을 활용하여", 관광학연구, 46(7), pp.75~96 (2022), 한국관광학회
- 임재필, "코로나(COVID-19)이후 항공운송산업의 수요회복 분석과 패러다임 전환", 관광연구저널, 36(2), pp.167~181 (2022), 한국관광연구학회[DOI]
- 장스위, "계절ARIMA 모형을 이용한 울산 고래관광 수요예측에 관한 연구", 관광레저연구, 34(9), pp.85~99 (2022), (사)한국관광레저학회
- 문화예술의 사회, 경제적 효과 분석 및 전망연구, "한국문화관광원", 1~226 (2015)
- 황경후, "계절 ARIMA 모형을 활용한 농촌관광 수요예측에 관한 연구 : 양평 외갓집 체험마을을 중심으로", 농어촌관광학회지, 21(1), pp.39~54 (2014)
- Anisa, M. P., "Forecasting Demand Factors of Tourist Arrivals in Indonesia’s Tourism Industry using Recurrent Neural Network", IOP Conference Series: Materials Science and Engineering (2021), IOP Publishing
- Bi, J. W., "Forecasting Daily Tourism Demand for Tourist Attractions with Big Data : An Ensemble Deep Learning Method", Journal of Travel Research, 61(8), pp.1719~1737 (2022)
- Chen, Y., "Forecasting Crude Oil Prices : A Deep Learning Based Model", Procedia Computer Science, 122, pp.300~307 (2017)
- Chitikela, G., "Artificial-Intelligence-Based Time-Series Intervention Models to Assess the Impact of the COVID-19 Pandemic on Tomato Supply and Prices in Hyderabad, India", Agronomy, 11(9), pp.1878~ (2021)
- Dong, Y., "A Time Series Attention Mechanism based Model for Tourism Demand Forecasting", Information Sciences, 628, pp.269~290 (2023)
- Fotiadis, A., "The Good, the Bad and the Ugly on COVID-19 Tourism Recovery", Annals of Tourism Research, 87, pp.103117~ (2021)
- Gil-Alana, L. A., "Seasonal Fractional Integration in the Spanish Tourism Quarterly Time Series", Journal of Travel Research, 42(4), pp.408~414 (2004)
- Hsieh, S. C., "Tourism Demand Forecasting based on an LSTM Network and Its Variants", Algorithms, 14(8), pp.243~ (2021)
- Koc, E., "An Analysis of Seasonality in Monthly per Person Tourist Spending in Turkish Inbound Tourism from a Market Segmentation Perspective", Tourism Management, 28(1), pp.227~237 (2007)
- Kourentzes, N., "Visitor Arrivals Forecasts Amid COVID-19 : A Perspective from the Africa Team", Annals of Tourism Research, 88, pp.103197~ (2021)
- Law, R., "Tourism Demand Forecasting : A Deep Learning Approach", Annals of Tourism Research, 75, pp.410~423 (2019)
- Wanying Li, "Short-Term Holiday Travel Demand Prediction for Urban Tour Transportation: A Combined Model Based on STC-LSTM Deep Learning Approach", KSCE Journal of Civil Engineering, 26(9), pp.4086~4102 (2022), 대한토목학회[DOI]
- Liu, A., "Visitor Arrivals Forecasts Amid COVID-19 : A Perspective from the Europe Team", Annals of Tourism Research, 88, pp.103182~ (2021)
- Neves, G. A., "Seasonal Autoregressive Integrated Moving Average Time Series Model for Tourism Demand: The Case of Sal Island, Cape Verde", Advances in Tourism, Technology and Systems: Selected Papers from ICOTTS 2021, 2, pp.11~21 (2022)
- Nurhasanah, D, "Forecasting International Tourist Arrivals in Indonesia Using SARIMA Model", Enthusiastic : International Journal of Applied Statistics and Data Science, 2(1), pp.19~25 (2022)
- Plzáková, L., "Impact of the COVID-19 Crisis on European Tourism", Tourism Economics, 28(1), pp.91~109 (2022)
- Qiu, R. T., "Visitor Arrivals Forecasts Amid COVID-19 : A Perspective from the Asia and Pacific Team", Annals of Tourism Research, 88, pp.103155~ (2021)
- Seong, B., "Intervention Analysis based on Exponential Smoothing Methods : Applications to 9", 11 and COVID-19 Effects, 2021, pp.98, 290~301
- Song, H., "Tourism Demand Modelling and Forecasting : A Review of Recent Research", Tourism Management, 29(2), pp.203~220 (2008)
- Song, H., "Tourism Forecasting Competition in the Time of COVID-19", Annals of Tourism Research, 88, pp.103198~ (2021)
- Song, H., "Tourism Forecasting Competition in the Time of COVID-19 : An Assessment of Ex Ante Forecasts", Annals of Tourism Research, 96, pp.103445~ (2022)
- Song, H., "A Review of Research on Tourism Demand Forecasting : Launching the Annals of Tourism Research Curated Collection on Tourism Demand Forecasting", Annals of Tourism Research, 75, pp.338~362 (2019)
- Van Doorn, J. W., "Tourism Forecasting and the Policymaker : Criteria of Usefulness", Tourism Management, 5(1), pp.24~39 (1984)
- Zhang, Y., "Tourism Demand Forecasting : A Decomposed Deep Learning Approach", Journal of Travel Research, 60(5), pp.981~997 (2021)
- Zhang, H., "Forecasting Tourism Recovery Amid COVID-19", Annals of Tourism Research, 87, pp.103149~ (2021)