Analisis Kinerja Algoritma Machine Learning Dalam Prediksi Data Deret Waktu Wisatawan Mancanegara Ke Bali

A.A Istri Candra Manika Dewi, Vania Noverina, Azka Widya Rahmawati, Agung Widiyanto, Atika Ratna Dewi

Abstract


Pariwisata Bali pascapandemi menghadapi fluktuasi ekstrem kedatangan wisatawan mancanegara. Kegagalan memprediksi pola deret waktu yang sarat anomali ini dapat menyebabkan inefisiensi alokasi sumber daya operasional. Oleh karena itu, penelitian ini membandingkan kinerja algoritma Linear Regression, Random Forest, dan Support Vector Regression (SVR) untuk merumuskan kerangka peramalan yang paling adaptif. Data historis bulanan kunjungan wisatawan dari tahun 1982 hingga 2025 diproses menggunakan rekayasa fitur ekstensif yang mencakup efek lag, pola musiman tahunan, serta indikator pandemi. Evaluasi komparatif metrik kesalahan dilakukan melalui strategi validasi bertahap: chronological split, expanding-window cross-validation, dan final holdout 2024-2025. Hasil evaluasi menunjukkan bahwa Linear Regression menjadi model terbaik secara keseluruhan yang mampu mengungguli metode benchmark dengan tingkat WAPE terendah sebesar 8,14 persen pada pengujian akhir. Walaupun Random Forest terbukti lebih tangguh mengenali fluktuasi nonlinier pada fase pemulihan dan SVR konsisten kurang optimal, ketiga model menurun drastis saat menghadapi anomali pandemi ekstrem. Penelitian ini menunjukkan bahwa kecocokan model dengan dinamika perubahan data dari waktu ke waktu lebih penting daripada sekadar kerumitan matematis algoritma dalam mendukung perencanaan strategis pariwisata di masa mendatang.

Keywords


machine learning; peramalan; regresi linier; time series; wisatawan mancanegara

References


S. Jiao and J. Chen, "Forecasting tourist arrivals using machine learning and internet search index," Tourism Economics, vol. 29, no. 3, pp. 642-663, 2023. DOI: 10.1177/13548166221142512

M. Wasesa, M. E. N. Siregar, A. N. Hidayanto, and M. I. N. Sugiarto, "Machine learning models for predicting international tourist arrivals in Indonesia during the COVID-19 pandemic: a multisource Internet data approach," Journal of Tourism Futures, vol. 9, no. 1, pp. 1-17, 2022. DOI: 10.1108/JTF-10-2021-0239

N. Antonakakis, I. Chatziantoniou, and G. Filis, "Tourism and uncertainty: a machine learning approach," Current Issues in Tourism, vol. 27, no. 4, pp. 1-20, 2024. DOI: 10.1080/13683500.2024.2370380

X. Li, K. F. Law, F. Vu, and J. Rong, "Tourism forecasting: A review of methodological developments," Annals of Tourism Research, vol. 91, p. 103328, 2021. DOI: 10.1016/j.annals.2021.103328

Y. Liu, H. Wang, and J. Chen, "Tourism demand forecasting using a hybrid deep learning model," Expert Systems with Applications, vol. 207, p. 118002, 2022. DOI: 10.1016/j.eswa.2022.118002

H. J. Kim, J. Lee, and Y. K. Lee, "Comparing machine learning techniques for tourism demand forecasting," Annals of Tourism Research Empirical Insights, vol. 3, no. 2, p. 100067, 2022. DOI: 10.1016/j.annale.2022.100067

J. Chen, Z. Ying, C. Zhang, and T. Balezentis, "Forecasting tourism demand with search engine data: A hybrid machine learning approach," Tourism Management, vol. 104, p. 104490, 2024. DOI: 10.1016/j.tourman.2024.104490

C. S. K. Dash, A. K. Behera, S. Dehuri, and S. B. Cho, "Time series forecasting of tourist arrivals using machine learning algorithms," International Journal of Information Management Data Insights, vol. 3, no. 1, p. 100155, 2023. DOI: 10.1016/j.jjimei.2023.100155

X. Zhang, Q. Song, and Y. Liu, "A comparative study of linear and non-linear machine learning models for tourism demand forecasting," Information Processing & Management, vol. 60, no. 2, p. 103211, 2023. DOI: 10.1016/j.ipm.2022.103211

A. P. Sohibien et al., "Hybrid GSTAR-Machine Learning Model for Forecasting Tourists Numbers in Yogyakarta," ZERO: Jurnal Sains, Matematika dan Terapan, vol. 8, no. 1, pp. 45-58, 2024. DOI not available-official link provided: https://jurnal.uinsu.ac.id/index.php/zero/article/view/26381

F. R. E. Mulyani, "Prediction of tourist visits to Bali using Support Vector Regression," Journal of Physics: Conference Series, vol. 1836, p. 012042, 2021. DOI: 10.1088/1742-6596/1836/1/012042

H. Zhang, G. Li, and B. Song, "Spatial-temporal tourism demand forecasting with machine learning models," Tourism Management Perspectives, vol. 42, p. 100958, 2022. DOI: 10.1016/j.tmp.2022.100958

N. Yu and J. Chen, "Design of Machine Learning Algorithm for Tourism Demand Prediction," Computational and Mathematical Methods in Medicine, vol. 2022, Art. no. 6352381, 2022, doi: 10.1155/2022/6352381.

V. I. Kontopoulou, A. D. Panagopoulos, I. Kakkos, and G. K. Matsopoulos, "A Review of ARIMA vs. Machine Learning Approaches for Time Series Forecasting in Data Driven Networks," Future Internet, vol. 15, no. 8, p. 255, 2023, doi: 10.3390/fi15080255.

L. Peng, L. Wang, X.-Y. Ai, and Y.-R. Zeng, "Forecasting Tourist Arrivals via Random Forest and Long Short-Term Memory," Cognitive Computation, vol. 13, no. 1, pp. 125–138, 2021, doi: 10.1007/s12559-020-09747-z.

S. Bouhaddour, M. Sbihi, F. Guerouate, and C. Saadi, “Assessing Tourism Prediction Models: A Comparative Study of SARIMA, Random Forest, and LSTM, Considering Nonlinear Trends and the Influence of COVID-19,” Ingénierie des Systèmes d’Information, vol. 29, no. 6, pp. 2443–2454, 2024, doi: 10.18280/isi.290631.

K. J. Waciko, L. A. Susanti, Muayyad, and R. N. Fakhrurozi, “Forecasting tourist arrivals in Bali: A grid search-tuned comparative study of Random Forest, XGBoost, and a hybrid RF-XGBoost model,” Inferensi, vol. 8, no. 3, 2025, doi: 10.12962/j27213862.v8i3.23334.


Refbacks

  • There are currently no refbacks.


Editorial Office :

Prosiding SENDIKO (Seminar Nasional Hasil Penelitian & Pengabdian Masyarakat Bidang Ilmu Komputer)
Published by Universitas PGRI Madiun
Managed by Program Studi Sistem Informasi Fakultas Teknik Universitas PGRI Madiun
Address Jl. Auri 14-16 Kota Madiun Kampus III Universitas PGRI Madiun 63118
Website http://prosiding.unipma.ac.id/index.php/sendiko/index
Email [email protected]

e-ISSN:  3025-4604