Forecasting Foreign Tourist Arrivals in Indonesia Using Google Trends Index as Exogenous Variable: A Comparative Study of SARIMAX and LSTM Models
DOI:
https://doi.org/10.30871/jaic.v10i2.12384Keywords:
Time Series Forecasting, Google Trends, SARIMAX, LSTM, Deep Learning, Applied Informatics, Tourism DemandAbstract
The rapid integration of Big Data into predictive modeling offers a solution to the
latency issues inherent in official statistical releases. This study investigates the
computational efficacy of integrating Google Trends Index (GTI) as an exogenous
variable for forecasting foreign tourist arrivals in Indonesia. We perform a
comparative performance analysis between a linear stochastic model, Seasonal
Autoregressive Integrated Moving Average with Exogenous Regressors
(SARIMAX), and a Deep Learning architecture, Long Short-Term Memory
(LSTM), using monthly time-series data from 2017 to 2024. Despite the theoretical
capability of LSTM to capture complex non-linear dependencies, empirical results
demonstrate that the SARIMAX model achieves superior accuracy with a Mean
Absolute Percentage Error (MAPE) of 5.85%, significantly outperforming the
LSTM model (MAPE 9.29%). This study provides critical insight into the "Model
Complexity vs. Data Availability" trade-off in applied computing, suggesting that
for aggregate macro-level data with limited sample sizes and strong seasonality,
parsimonious econometric models remain more robust than data-hungry neural
networks. The findings validate the utility of search engine query data in enhancing
predictive algorithms for tourism informatics.
Downloads
References
[1] Badan Pusat Statistik, “Jumlah Kunjungan Wisatawan Mancanegara ke Indonesia per Bulan, 2017--2024,” 2025. [Online]. Available: https://www.bps.go.id
[2] Z. Xiang and U. Gretzel, “Role of social media in online travel information search,” Tour. Manag., vol. 31, no. 2, pp. 179–188, 2010, doi: 10.1016/j.tourman.2009.02.016.
[3] P. F. Bangwayo-Skeete and R. W. Skeete, “Can {Google} data improve the forecasting accuracy of tourist arrivals? {Mixed}-data sampling approach,” Tour. Manag., vol. 46, pp. 454–464, 2015, doi: 10.1016/j.tourman.2014.07.014.
[4] U. Gunter and I. Onder, “Forecasting city arrivals with {Google Analytics},” Ann. Tour. Res., vol. 61, pp. 199–212, 2016, doi: 10.1016/j.annals.2016.10.007.
[5] X. Li, R. Law, Y. Ren, and X. Wu, “Forecasting tourism demand with {KPSS}, {ADF}, {PP} tests and search trends data: Evidence from {China},” J. Hosp. & Tour. Res., vol. 45, no. 3, pp. 1–26, 2021, doi: 10.1177/1096348020985398.
[6] G. Toth and C. Brown, “A meta-analytic review of internet search data in tourism demand forecasting,” J. Travel Res., vol. 62, no. 4, pp. 845–862, 2023, doi: 10.1177/00472875221105461.
[7] S. Hochreiter and J. Schmidhuber, “Long {Short-Term Memory},” Neural Comput., vol. 9, no. 8, pp. 1735–1780, 1997, doi: 10.1162/neco.1997.9.8.1735.
[8] S. Makridakis, E. Spiliotis, and V. Assimakopoulos, “Statistical and {Machine Learning} forecasting methods: {Concerns} and ways forward,” PLoS One, vol. 13, no. 3, p. e0194889, 2018, doi: 10.1371/journal.pone.0194889.
[9] S. Cankurt and A. Subasi, “Tourism demand modelling and forecasting using data mining techniques in multivariate time series: A case study in {Turkey},” Turkish J. Electr. Eng. & Comput. Sci., vol. 23, pp. 1–18, 2015, doi: 10.3906/elk-1311-134.
[10] U. Gunter, “Conditional tourism forecasting with artificial neural networks: {Evidence} from {Austria},” Int. J. Hosp. Manag., vol. 89, p. 102541, 2020, doi: 10.1016/j.ijhm.2020.102541.
[11] H. Song, R. T. R. Qiu, and J. Park, “A review of research on tourism demand forecasting: {Launching} the {Annals of Tourism Research Curated Collection} on tourism demand forecasting,” Ann. Tour. Res., vol. 75, pp. 338–362, 2019, doi: 10.1016/j.annals.2018.12.001.
[12] I. Önder and U. Gunter, “Pitfalls in {Google Trends}-based forecasting: Addressing keyword selection bias,” Tour. Econ., vol. 28, no. 5, pp. 1–20, 2022, doi: 10.1177/13548166211005895.
[13] K. Volchek, A. Liu, H. Song, and D. Buhalis, “Forecasting tourist arrivals at attractions: {Search} engine empowered methodologies,” Tour. Econ., vol. 25, no. 3, pp. 425–447, 2019, doi: 10.1177/1354816618811558.
[14] Z. Xiang, V. P. Magnini, and D. R. Fesenmaier, “Information technology and consumer behavior in travel and tourism: {Insights} from travel planning using the internet,” J. Retail. Consum. Serv., vol. 22, pp. 244–249, 2015, doi: 10.1016/j.jretconser.2014.08.005.
[15] X. Huang, H. Zhang, and Y. Endo, “{Google} flight search data as a predictor of international tourism: {A} case study of {Japan},” Tour. Manag. Perspect., vol. 36, p. 100731, 2020, doi: 10.1016/j.tmp.2020.100731.
[16] J. F. Hair, W. C. Black, B. J. Babin, and R. E. Anderson, Multivariate Data Analysis, 8th ed. Cengage Learning, 2019.
[17] G. C. Chow, “Tests of equality between sets of coefficients in two linear regressions,” Econometrica, vol. 28, no. 3, pp. 591–605, 1960, doi: 10.2307/1910133.
[18] P.-F. Pai and C.-S. Lin, “A hybrid {ARIMA} and support vector machines model in stock price forecasting,” Omega, vol. 33, no. 6, pp. 497–505, 2005, doi: 10.1016/j.omega.2004.07.024.
[19] R. J. Hyndman and G. Athanasopoulos, Forecasting: {Principles} and {Practice}, 3rd ed. Melbourne, Australia: OTexts, 2021. [Online]. Available: https://otexts.com/fpp3/
[20] B. Lim and S. Zohren, “Time-series forecasting with deep learning: {A} survey,” Philos. Trans. R. Soc. A, vol. 379, no. 2194, p. 20200209, 2021, doi: 10.1098/rsta.2020.0209.
[21] Y. Fang, H. Guo, Y. Liu, and H. Zhao, “Transfer learning for tourism demand forecasting with limited data,” Expert Syst. Appl., vol. 213, p. 118956, 2023, doi: 10.1016/j.eswa.2022.118956.
[22] C. D. Lewis, Industrial and Business Forecasting Methods. London: Butterworth-Heinemann, 1982.
[23] E. S. Silva, H. Hassani, S. Heravi, and X. Huang, “Forecasting tourism demand with {Google Trends}: {A} competing modelling approach,” J. Travel Res., vol. 58, no. 1, pp. 142–161, 2019, doi: 10.1177/0047287518767390.
[24] World Tourism Organization, “Tourism Recovery Tracker,” 2023. [Online]. Available: https://www.unwto.org/tourism-data/global-and-regional-tourism-performance
[25] D. A. Dickey and W. A. Fuller, “Distribution of the estimators for autoregressive time series with a unit root,” J. Am. Stat. Assoc., vol. 74, no. 366, pp. 427–431, 1979, doi: 10.2307/2286348.
[26] D. N. Gujarati and D. C. Porter, Basic Econometrics, 5th ed. New York: McGraw-Hill Education, 2009.
[27] Yahoo Finance, “{IDR/USD} Exchange Rate Historical Data (2017--2024),” 2025. [Online]. Available: https://finance.yahoo.com/quote/IDR=X
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Entis Sutisna, Rahma Dafitri, Dian Daryani
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
