PERBANDINGAN MODEL PREDIKSI SARIMA, LSTM, DAN PROPHET DALAM PREDIKSI VOLUME BONGKAR-MUAT KAPAL
DOI:
https://doi.org/10.30997/jvs.v11i2.22161Abstract
Accurately predicting ship loading and unloading volumes at ports is essential for optimizing operations and strategic planning. This study compares three time series forecasting models: SARIMA, LSTM, and Prophet, to predict ship loading and unloading volumes at Tanjung Priok, Indonesia's busiest port. The dataset covers the period from January 2017 to August 2025 in monthly increments. Hyperparameter tuning was performed on each model to determine the optimal hyperparameter values. Model performance was evaluated on the testing dataset using the Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and accuracy metrics. Based on these four metrics, SARIMA had the best performance with an accuracy rate of 87.97%, followed by the LSTM model at 85.38%, and the Prophet model at 69.40%. SARIMA can capture seasonal patterns and trends in loading and unloading data, making it useful for decision-making related to ship scheduling, crane allocation, and dock management. This study emphasizes the importance of selecting a model based on the characteristics of the data and demonstrates that traditional statistical models, such as SARIMA, are competitive with deep learning models for time series with strong seasonality.
References
Cintani, M., dkk. (2025). Evaluation of the SARIMA and Prophet Models in Forecasting Ship Passenger Numbers at Balikpapan Port. Jambura Journal of Mathematics, 7(2), 120–128. https://doi.org/10.37905/jjom.v7i2.31606
D. Li, “Feature Selection Based on Stock Prediction Model,” J. Phys. Conf. Ser., vol. 2386, no. 1, 2022, doi: 10.1088/1742-6596/2386/1/012021
Ensafi, Y., dkk. (2022). Time-series forecasting of seasonal items sales using machine learning – A comparative analysis. International Journal of Information Management Data Insights. 2 (1). https://doi.org/10.1016/j.jjimei.2022.100058
Fesalbon, D. (2024). Forecasting Ferry Passenger Flow Using Long-Short TermMemory Neural Networks. International Journal of Scientific Research and Engineering Development, 7(3), https://doi.org/10.48550/arXiv.2405.02098
Fernando, Z., & Mailoa, E. (2024). Implementasi Time series Dalam Prediksi Jumlah Keberangkatan Penumpang di Pelabuhan Tanjung Perak. Jutisi : Jurnal Ilmiah Teknik Informatika Dan Sistem Informasi, 13(2), 1296-1303. doi:http://dx.doi.org/10.35889/jutisi.v13i2.1998
Jiang, F., Xie, G., dan Wang, S. Forecasting Port Container Throughput with Deep Learning Approach. The 5th International Conference on Computer Science and Application Engineering (CSAE 2021), October 19-21, 2021, Sanya, China, DOI: https://doi.org/10.1145/3487075.3487173
Khoiriyah, N. S., dkk. (2023). Peramalan Jumlah Penumpang Kapal di Pelabuhan Balikpapan dengan SARIMA. Jurnal Statistika dan Komputasi. 2(2):76-82. Doi: 10.32665/statkom.v2i2.2303.
Lee, G.-C., & Bang, J.-Y. (2024). Forecasting Container Throughput of Singapore Port Considering Various Exogenous Variables Based on SARIMAX Models. Forecasting, 6 (3), 748-760. https://doi.org/10.3390/forecast6030038
Li, M. (2024). Port Throughput Forecast Based on ARIMA Model-Take Tianjin Port as an Example. Highlights in Science, Engineering and Technology, 105, 11-17. https://doi.org/10.54097/dv0kzs60
Munim, Z. H., dkk. (2023). Forecasting container throughput of major Asian ports using the Prophet and hybrid time series models. The Asian Journal of Shipping and Logistics, 39 (2), 67-66. https://doi.org/10.1016/j.ajsl.2023.02.004.
Negara, R. I. P. (2021). Peramalan Jumlah Penumpang Kapal di Pelabuhan Pantai Baru dengan Metode Sarima Dan Winter’s Exponential Smoothing. Jurnal Statistika Terapan (ISSN 2807-6214), 1(1), 63–78.
Oh, J.H., dkk. (2022). Throughput Prediction of Pohang Port using Time series Data: Application of SARIMA, Prophet and Neural Prophet. Korea Trade Review. 47 (6). 291-305. https://doi.org/10.22659/KTRA.2022.47.6.291
Ratmoko, H., & Zuliarso, E. (2025). Time Series Forecasting for Container Throughput Using SARIMA and LSTM: A Case Study of Tanjung Emas Port, Semarang. Maritime Park: Journal of Maritime Technology and Society, 4(3), 232–242. https://doi.org/10.62012/mp.vi.45866
Ricardianto, P., Suhalis, A., Siarit, D. P. (2018). Integrasi antara Dwelling Time dan Bingkar Muat Peti Kemas Pelabuhan Tanjung Priok. Jurnal Manajemen Transportasi & Logistik. 5(3). doi: 10.54324/j.mtl.v5i3.265
Rismawati, Alwi, W., Sauddin, A., & Adiatma. (2024). Peramalan Jumlah Penumpang Kapal Laut Menggunakan Metode Time series Machine learning di PT Pelabuhan Indonesia (Persero) Ragional 4 (Studi Kasus Pada Pelabuhan Soekarno Hatta Makassar). Jurnal MSA (Matematika Dan Statistika Serta Aplikasinya), 12(2), 68–78. https://doi.org/10.24252/msa.v12i2.51076.
Riung, R., Nainggolan, N., & Langi, Y.A.R, (2024). Peramalan Jumlah Penumpang Kapal Laut di Pelabuhan Melonguane Kabupaten Kepulauan Talaud Menggunakan Metode SARIMA. Jurnal MIPA (JM). Vol. 13 No. 2. DOI: https://doi.org/10.35799/jm.v13i2.55741
Saber, dkk. (2025). High-accuracy prediction of vessels’ estimated time of arrival in seaports: A hybrid machine learning approach. Maritime Transport Research. Vol 8. https://doi.org/10.1016/j.martra.2025.100133
Xiao, Y., dkk. (2025). Analyzing and Forecasting Container Throughput With a Hybrid Decomposition-Reconstruction-Ensemble Method: A Study of Two China Ports. Journal of Forecasting. 44(4). https://doi.org/10.1002/for.3253
Zhang, D., dkk. (2024). A novel hybrid deep-learning framework for medium-term container throughput forecasting: an application to China’s Guangzhou, Qingdao and Shanghai hub ports. Marit Econ Logist 26, 44–73. https://doi.org/10.1057/s41278-024-00284-2
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Jurnal Visionida
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with Jurnal Visionida 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 4.0 International License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in Jurnal Visionida.
- 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 Jurnal Visionida.
- 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
