A Comparative Evaluation of Univariate Time Series Forecasting Models for Tourism Operational Indicators at Boom Marina Banyuwangi
Keywords:
Time Series Forecasting, Tourism Analytics, Random Forest Regressor, Deep Learning Models, Machine Learning Models, Univariate Prediction, Boom Mariana BanyuwangiAbstract
Accurate forecasting of a tourism operational indicator is crucial for planning and making informed decisions, but heterogeneity in temporal patterns prevents us from selecting a single optimal model. This research aims to compare univariate time-series forecasting models to identify the best model for each operational index in the Boom Marina Banyuwangi Tourism Area. Data on weekly ticketing_log from PT Pelindo Properti Indonesia covering seven input indicators were used, namely the number of tourists, total income, the number of motorcycles, the number of vehicles, the number of pedestrians, the cash payment amount, and the total parking fee. The flow of this study follows the CRISP-DM framework. It includes (i) data cleansing (using Z-score for winsorization), median imputation, daily-to-weekly aggregation, Robust Scaler normalization, (ii) sliding window formation (4, 8, 12 weeks), (iii) separation into training and test set with a ratio of 80:20. Seven models were used for comparison (BiLSTM, BiGRU, LSTM, GRU, Simple RNN, 1D-CNN, and a Random Forest Regressor) which performance was measured in terms of MAE or RMSE. The findings demonstrate that no single model performed best across all measures. Random Forest Regressor was the best predictor of four indicators: number of tourists (MAE = 0.5053; RMSE = 0.6532) and number of vehicles (MAE = 0.5904; RMSE = 0.7966). In contrast, BiGRU, BiLSTM, and Simple RNN achieved the best performance for total revenue, the number of motorcycles, and the number of pedestrians, respectively. These results imply that tree-based ensemble methods can capture nonlinear patterns, whereas recurrent neural networks are well-suited for indicators with strong temporal dependencies.
References
[1] UNWTO, International Tourism Highlights, 2020 Edition. World Tourism Organization (UNWTO), 2020. doi: 10.18111/9789284422456.
[2] N. P. Hentika and E. Agustina, “Tourism Marketing: Banyuwangi Regency Government Partnership with Local Mass Media in Banyuwangi,” Jurnal Sejarah Pendidikan Dan Humaniora (Santhet), vol. 8, no. 1, 2024, doi: 10.36526/santhet.v8i1.3597.
[3] A. Kumar Dubey, A. Kumar, V. García-Díaz, A. Kumar Sharma, and K. Kanhaiya, “Study and analysis of SARIMA and LSTM in forecasting time series data,” Sustainable Energy Technologies and Assessments, vol. 47, Oct. 2021, doi: 10.1016/j.seta.2021.101474.
[4] T. Falatouri, F. Darbanian, P. Brandtner, and C. Udokwu, “Predictive Analytics for Demand Forecasting - A Comparison of SARIMA and LSTM in Retail SCM,” in Procedia Computer Science, Elsevier B.V., 2022, pp. 993–1003. doi: 10.1016/j.procs.2022.01.298.
[5] F. Petropoulos and E. Spiliotis, “The Wisdom of the Data: Getting the Most Out of Univariate Time Series Forecasting,” Sep. 01, 2021, MDPI. doi: 10.3390/forecast3030029.
[6] D. H. Hopfe, K. Lee, and C. Yu, “Short-term forecasting airport passenger flow during periods of volatility: Comparative investigation of time series vs. neural network models,” J Air Transp Manag, vol. 115, Mar. 2024, doi: 10.1016/j.jairtraman.2023.102525.
[7] A. Nicholas, “Forecasting US overseas travelling with univariate and multivariate models,” J Forecast, vol. 40, no. 6, pp. 963–976, Sep. 2021, doi: 10.1002/for.2760.
[8] S. C. Hsieh, “Tourism demand forecasting based on an lstm network and its variants,” Algorithms, vol. 14, no. 8, Aug. 2021, doi: 10.3390/a14080243.
[9] A. Salamanis, G. Xanthopoulou, D. Kehagias, and D. Tzovaras, “LSTM-Based Deep Learning Models for Long-Term Tourism Demand Forecasting,” Electronics (Switzerland), vol. 11, no. 22, Nov. 2022, doi: 10.3390/electronics11223681.
[10] D. Quoc Nguyen, M. Nguyet Phan, and I. Zelinka, “Periodic Time Series Forecasting with Bidirectional Long Short-Term Memory: Periodic Time Series Forecasting with Bidirectional LSTM,” in ACM International Conference Proceeding Series, Association for Computing Machinery, Jan. 2021, pp. 60–64. doi: 10.1145/3453800.3453812.
[11] J. W. Bi, H. Li, and Z. P. Fan, “Tourism demand forecasting with time series imaging: A deep learning model,” Ann Tour Res, vol. 90, Sep. 2021, doi: 10.1016/j.annals.2021.103255.
[12] Y. Dong, L. Xiao, J. Wang, and J. Wang, “A time series attention mechanism based model for tourism demand forecasting,” Inf Sci (N Y), vol. 628, pp. 269–290, May 2023, doi: 10.1016/j.ins.2023.01.095.
[13] S. Bouhaddour, C. Saadi, I. Bouabdallaoui, M. Sbihi, and F. Guerouate, “A Novel Hybrid Approach for Daily Tourism Arrival Forecasting: The PROPHET-Bayesian Gaussian Process-Forward Neural Network Model,” Ingenierie des Systemes d’Information, vol. 28, no. 4, pp. 833–842, Aug. 2023, doi: 10.18280/isi.280404.
[14] A. L. Toba, S. Kulkarni, W. Khallouli, and T. Pennington, “Long-Term Traffic Prediction Using Deep Learning Long Short-Term Memory,” Smart Cities, vol. 8, no. 4, Aug. 2025, doi: 10.3390/smartcities8040126.
[15] C. Dewangga and S. Hansun, “Enforcement of Community Activity Restrictions Level Prediction in Jakarta Using Long Short-Term Memory Network,” Journal of Applied Data Sciences, vol. 5, no. 4, pp. 1782–1789, Dec. 2024, doi: 10.47738/jads.v5i3.318.
[16] H. Sun, Y. Yang, Y. Chen, X. Liu, and J. Wang, “Tourism demand forecasting of multi-attractions with spatiotemporal grid: a convolutional block attention module model,” Information Technology and Tourism, vol. 25, no. 2, pp. 205–233, Jun. 2023, doi: 10.1007/s40558-023-00247-y.
[17] I. Vasenska, “Comparative Analysis of Machine Learning and Deep Learning Models for Tourism Demand Forecasting with Economic Indicators,” FinTech, vol. 4, no. 3, Sep. 2025, doi: 10.3390/fintech4030046.
[18] E. houssin Ouassou and H. Taya, “Forecasting Regional Tourism Demand in Morocco from Traditional and AI-Based Methods to Ensemble Modeling,” Forecasting, vol. 4, no. 2, pp. 420–437, Jun. 2022, doi: 10.3390/forecast4020024.
[19] H. Mukhtar et al., “Advanced tourist arrival forecasting: a synergistic approach using LSTM, Hilbert-Huang transform, and random forest,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 38, no. 1, p. 517, Apr. 2025, doi: 10.11591/ijeecs.v38.i1.pp517-526.
[20] J. Bravo, R. Alarcón, C. Valdivia, and O. Serquén, “Application of Machine Learning Techniques to Predict Visitors to the Tourist Attractions of the Moche Route in Peru,” Sustainability (Switzerland), vol. 15, no. 11, Jun. 2023, doi: 10.3390/su15118967.
[21] H. Laaroussi, F. Guerouate, and M. Sbihi, “Deep Learning Framework for Forecasting Tourism Demand,” in 2020 IEEE International Conference on Technology Management, Operations and Decisions, ICTMOD 2020, Institute of Electrical and Electronics Engineers Inc., Nov. 2020. doi: 10.1109/ICTMOD49425.2020.9380612.
[22] J. Lemmel et al., “Deep-Learning vs Regression: Prediction of Tourism Flow with Limited Data,” Jun. 2022, doi: 10.48550/arXiv.2206.13274.
[23] C. Schröer, F. Kruse, and J. M. Gómez, “A systematic literature review on applying CRISP-DM process model,” in Procedia Computer Science, Elsevier B.V., 2021, pp. 526–534. doi: 10.1016/j.procs.2021.01.199.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Muhammad Ilham Choiruddin, Ego Widiarto (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
