A Comparative Study of AutoSARIMAX and Long Short-Term Memory Models for Tourist Arrival Forecasting

Dian Saptarini; Dian Syafitri Chani Saputri; Helna Wardhana; Galih Hendro Martono

doi:10.30812/varian.v9i1.5771

Authors

Dian Saptarini Universitas Bumigora, Mataram, Indonesia
Dian Syafitri Chani Saputri Universitas Bumigora, Mataram, Indonesia
Helna Wardhana Universitas Bumigora, Mataram, Indonesia
Galih Hendro Martono Universitas Bumigora, Mataram, Indonesia

DOI:

https://doi.org/10.30812/varian.v9i1.5771

Keywords:

AutoSARIMAX, Deep Learning, Forecasting, LSTM, Tourism

Abstract

This study aims to predict the number of tourist arrivals in West Nusa Tenggara (NTB) Province using two forecasting approaches: AutoRegressive Integrated Moving Average with Exogenous Variables (AutoSARIMAX) and Long Short-Term Memory (LSTM). The dataset was obtained from the Central Bureau of Statistics (BPS) of NTB and consists of international and domestic tourist arrivals and monthly inflation rates for the period 2014–2023. The research process includes data collection, preprocessing, model construction, and result evaluation. The AutoSARIMAX model is applied to capture linear relationships with exogenous variables, while LSTM is employed to model long-term nonlinear patterns. The findings reveal that the LSTM model achieved better forecasting performance, with a Mean Absolute Percentage Error (MAPE) of 2.65%, which is lower than AutoSARIMAX with 3.25%. Nevertheless, AutoSARIMAX provides valuable interpretability regarding the influence of inflation on tourist arrivals. Overall, the comparison between the two models indicates that LSTM is more effective for time-series forecasting of tourist arrivals, while AutoSARIMAX remains useful for analyzing causal relationships. These insights can support decision-making in tourism planning, particularly in anticipating fluctuations driven by economic and external factors.

Downloads

Download data is not yet available.

References

Berikut adalah daftar referensi tersebut yang telah dirapikan dari pemutusan baris (line breaks), spasi berlebih, dan kesalahan pemisahan tautan agar menjadi format yang bersih dan profesional:

Badan Pusat Statistik Indonesia. (2023). Statistik kunjungan wisatawan mancanegara 2023. https://www.bps.go.id/id/publication/2024/04/05/0ba2b8f3f4f15dd18799f0c0/statistik-kunjungan-wisatawan-mancanegara-2023.html

Balli, H. O., Tsui, W. H. K., & Balli, F. (2019). Modelling the volatility of international visitor arrivals to New Zealand. Journal of Air Transport Management, 75, 204–214. https://doi.org/10.1016/j.jairtraman.2018.10.002

Elshewey, A. M., Shams, M. Y., Elhady, A. M., Shohieb, S. M., Abdelhamid, A. A., Ibrahim, A., & Tarek, Z. (2022). A Novel WD-SARIMAX Model for Temperature Forecasting Using Daily Delhi Climate Dataset. Sustainability, 15(1), 757. https://doi.org/10.3390/su15010757

Ennagoura, D., Kehal, K. E., Berdai, A., Merzouk, S., Fahssi, K. E., Mahjouby, M. E., Far, M. E., & Bennani, M. T. (2026). A Comparative Evaluation of SARIMAX, LSTM, and Prophet Models for Cryptocurrency Price Trend Prediction. Engineering, Technology & Applied Science Research, 16(2), 33146–33151. https://doi.org/10.48084/etasr.15554

Hidayati, S. N. (2022). Determinan Indeks Pembangunan Manusia di Provinsi Nusa Tenggara Barat Tahun 2015 – 2020. Digital Bisnis: Jurnal Publikasi Ilmu Manajemen dan E-Commerce, 1(3), 279–297. https://doi.org/10.30640/digital.v1i3.593

Juliarto, H. K., Purnamasari, I., & Prangga, S. (2024). Peramalan Peredaran Uang Kartal di Indonesia Menggunakan Model Hybrid SARIMAX-Neural Network. Jurnal Gaussian, 12(4), 465–476. https://doi.org/10.14710/j.gauss.12.4.465-476

Manakane, S. E., Latue, P. C., Somae, G., & Rakuasa, H. (2023). The Role of Geography Research in Supporting Sustainable Development in Ambon City, Indonesia: A Review. Sinergi International Journal of Economics, 1(2), 64–75. https://doi.org/10.61194/economics.v1i2.67

Mukarromah, N. S., Manulang, W., Maemunah, M., Mayasari, D., Hafsah, H., & Sakban, A. (2023). Analisis Peluang dan Sumber Kekayaan dari Pembangunan di Nusa Tenggara Barat. Seminar Nasional Paedagoria, 3(0), 302–313. https://journal.ummat.ac.id/index.php/fkip/article/view/16319

Nontapa, C., Kesamoon, C., Kaewhawong, N., & Intrapaiboon, P. (2021). A New Hybrid Forecasting Using Decomposition Method with SARIMAX Model and Artificial Neural Network. International Journal of Mathematics and Computer Science, 16(4), 1341–1354.

Purnaningrum, E., & Ariqoh, I. (2019). Google Trends Analytics dalam Bidang Pariwisata. Majalah Ekonomi, 24(2), 232–243. https://doi.org/10.36456/majeko.vol24.no2.a2069

Purwahita, A. R. M., Wardhana, P. B. W., Ardiasa, I. K., & Winia, I. M. (2021). Dampak Covid-19 terhadap Pariwisata Bali Ditinjau dari Sektor Sosial, Ekonomi, dan Lingkungan (Sebuah Tinjauan Pustaka). Jurnal Kajian dan Terapan Pariwisata, 1(2), 68–80. https://doi.org/10.53356/diparojs.v1i2.29

Rahayu, I., Marwati, R., & Rachmatin, D. (2022). Peramalan jumlah penderita dbd di provinsi jawa barat dengan metode hybrid sarimax-ann. JMT : Jurnal Matematika dan Terapan, 4(2), 9–19. https://doi.org/10.21009/jmt.4.2.2

Ridla, M. A., Azise, N., & Rahman, M. (2023). Perbandingan Model Time Series Forecasting dalam Memprediksi Jumlah Kedatangan Wisatawan dan Penumpang Airport. SIMKOM, 8(1), 1–14. https://doi.org/10.51717/simkom.v8i1.103

Saiman, S., & Lasdianti, S. G. (2022). Studi Pembangunan Infrastruktur Pariwisata. Jurnal Kawistara, 12(3), 341. https://doi.org/10.22146/kawistara.65838

Saranj, A., & Zolfaghari, M. (2022). The electricity consumption forecast: Adopting a hybrid approach by deep learning and ARIMAX-GARCH models. Energy Reports, 8, 7657–7679. https://doi.org/10.1016/j.egyr.2022.06.007

Soeswoyo, D. M., Jeneetica, M., Dewi, L., Dewantara, M. H., & Asparini, P. S. (2021). Tourism Potential and Strategy to Develop Competitive Rural Tourism in Indonesia. International Journal of Applied Sciences in Tourism and Events, 5(2), 131–141. https://doi.org/10.31940/ijaste.v5i2.131-141

Sultana, N., Hossain, S. M. Z., Almuhaini, S. H., & Dustegor, D. (2022). Bayesian Optimization Algorithm-Based Statistical and Machine Learning Approaches for Forecasting Short-Term Electricity Demand. Energies, 15(9), 3425. https://doi.org/10.3390/en15093425

Sung, J., Shi, X., Teske, S., & Li, M. (2025). Chinese natural gas phase-out pathways: A novel hybrid scenario-specific projection approach to achieve Net Zero. Energy, 328, 136387. https://doi.org/10.1016/j.energy.2025.136387

Sutisna, E., Dafitri, R., & Daryani, D. (2026). Forecasting Foreign Tourist Arrivals in Indonesia Using Google Trends Index as Exogenous Variable: A Comparative Study of SARIMAX and LSTM Models. Journal of Applied Informatics and Computing, 10(2), 1864–1871. https://doi.org/10.30871/jaic.v10i2.12384

Tangkudung, A. G. D., Rante, J. Z., Pakpahan, M., Putri, A., Puteri, A., Pribadi, D., Gosita, D. R., Rustandi, J., Cpr, J. J., Ghalib, K., Farieanna, R., Purnawirawati, S., Setiawan, S., & Bassuni, W. (2024). Inovasi Bisnis Pariwisata Indonesia Pasca Pandemi Covid-19. Jurnal Pendidikan Tambusai, 8(1), 657–667. https://doi.org/10.31004/jptam.v8i1.12444

Valguna, P. A., Dewanti, D., & Suparma, L. B. (2020). Dampak Perkembangan Pariwisata Pulau Lombok terhadap Pengembangan Bandar Udara Internasional Lombok. Jurnal Manajemen Aset Infrastruktur & Fasilitas, 4(3). https://doi.org/10.12962/j26151847.v4i3.7100

Wirawan, P. E., Octaviany, V., & Nuruddin, N. (2022, October 26). Pengantar pariwisata. Nilacakra.

Zhou, Y. (2021). Regional energy consumption prediction based on SARIMAX-LSTM model. Academic Journal of Computing & Information Science, 4(3). https://doi.org/10.25236/AJCIS.2021.040307