Perbandingan Algoritma LSTM dan ARIMA untuk Prediksi Jumlah Pengunjung Museum Airlangga Kota Kediri
DOI:
https://doi.org/10.29407/8gt0cc74Abstract
Museum Airlangga Kota Kediri masih menggunakan pencatatan jumlah pengunjung secara manual sehingga data kunjungan yang tersedia belum dapat dimanfaatkan secara optimal untuk mendukung pengambilan keputusan. Penelitian ini bertujuan untuk membandingkan performa algoritma Autoregressive Integrated Moving Average (ARIMA) dan Long Short-Term Memory (LSTM) dalam memprediksi jumlah pengunjung museum berdasarkan data historis kunjungan periode Januari 2024 hingga Maret 2026. Tahapan penelitian meliputi preprocessing data, pembangunan model, pengujian, dan evaluasi menggunakan Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), dan Mean Absolute Percentage Error (MAPE). Hasil penelitian menunjukkan bahwa model ARIMA memperoleh nilai MAE sebesar 3.6730, RMSE sebesar 6.9843, dan MAPE sebesar 247.5704%, sedangkan model LSTM memperoleh nilai MAE sebesar 2.9242, RMSE sebesar 7.1169, dan MAPE sebesar 155.2355%. Meskipun nilai RMSE ARIMA sedikit lebih rendah, model LSTM menghasilkan nilai MAE dan MAPE yang lebih baik sehingga secara keseluruhan memiliki performa prediksi yang lebih unggul. Hasil penelitian ini menunjukkan bahwa metode LSTM lebih efektif dalam memprediksi jumlah pengunjung museum yang memiliki pola data dinamis dan fluktuatif.
Keywords:
ARIMA, LSTM, Prediksi, Time Series, Wisata Museum##plugins.themes.default.displayStats.downloads##
References
[1] P. Nikolaou, “Museums and the Post-Digital: Revisiting Challenges in the Digital
Transformation of Museums,” Heritage, vol. 7, no. 3, pp. 1784–1800, Mar. 2024,
doi: 10.3390/heritage7030084.
[2] J. Q. H. Yap, Z. Kamble, A. T. H. Kuah, and D. Tolkach, “The impact of
digitalization and digitisation in museums on memory-making,” 2024, Routledge. doi:
10.1080/13683500.2024.2317912.
[3] S. Puspasari, R. Gustriansyah, and A. Sanmorino, “Forecasting a museum visit post
pandemic using exponential smoothing model,” JURNAL INFOTEL, vol. 15, no. 4,
pp. 309–316, Nov. 2023, doi: 10.20895/infotel.v15i4.949.
[4] K. Xu, J. Zhang, J. Huang, H. Tan, X. Jing, and T. Zheng, “Forecasting Visitor
Arrivals at Tourist Attractions: A Time Series Framework with the N-BEATS
for Sustainable Tourism,” Sustainability (Switzerland), vol. 16, no. 18, Sep. 2024,
doi: 10.3390/su16188227.
[5] K. Umam, “MIND (Multimedia Artificial Intelligent Networking Database
Perbandingan Metode ARIMA dan LSTM pada Prediksi Jumlah Pengunjung
Perpustakaan,” Journal MIND Journal | ISSN, vol. 8, no. 2, pp. 119–129, 2023,
doi: 10.26760/mindjournal.v8i2.119-129.
[6] A. Sherstinsky, “Fundamentals of Recurrent Neural Network (RNN) and Long ShortTerm Memory (LSTM) network,” Physica D, vol. 404, Mar. 2020, doi:
10.1016/j.physd.2019.132306.
[7] 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.
[8] E. Fuad, J. Siregar, and Y. Rizki, “Forecasting Tourist Arrivals with Partial Time
Series Data Using Long-Short Term Memory (LSTM),” The Asian Institute of
Research Engineering and Technology Quarterly Reviews, vol. 6, no. 1, pp. 56–
64, 2023, [Online]. Available: https://www.asianinstituteofresearch.org/
[9] S. Jurnal, A. Satrani, B. Krismono, and K. Hidjah, “Jurnal Sistem Informasi dan
Teknologi ( S I N T E K ) Hybrid Deep Learning untuk Prediksi Kunjungan Tamu Hotel”,
[Online]. Available: https://sintek.stmikku.ac.id/index.php/home
[10] P. Manandhar, H. Rafiq, E. Rodriguez-Ubinas, and T. Palpanas, “New
ForecastingMetrics Evaluated in Prophet, Random Forest, and Long Short-Term
Memory Models for Load Forecasting,” Energies (Basel)., vol. 17, no. 23, Dec.
2024, doi: 10.3390/en17236131.
Downloads
Published
Issue
Section
License
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:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment 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 acknowledgment 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.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
