Peramalan Penerimaan Iuran Program Jaminan Kehilangan Pekerjaan BPJS Ketenagakerjaan Menggunakan Metode Hybrid Prophet-BiLSTM
DOI:
https://doi.org/10.61626/jamsostek.v3i2.123Keywords:
BPJS Ketenagakerjaan, Jaminan Kehilangan Pekerjaan, Model Hybrid Prophet-BiLSTM, Perlindungan SosialAbstract
BPJS Ketenagakerjaan menyelenggarakan program Jaminan Kehilangan Pekerjaan (JKP) sebagai bentuk perlindungan sosial bagi pekerja yang mengalami pemutusan hubungan kerja. Fluktuasi penerimaan iuran JKP membutuhkan metode peramalan yang akurat sebagai dasar perencanaan keuangan untuk keberlanjutan program. Penelitian ini bertujuan untuk mengembangkan model peramalan penerimaan iuran JKP menggunakan pendekatan Hybrid Prophet– Bidirectional Long Short-Term Memory (BiLSTM) yang dikombinasikan melalui Linear Optimal Weighting Estimator (LOWE). Data yang digunakan berupa data bulanan iuran JKP periode Februari 2021 hingga Agustus 2025. Melalui evaluasi kinerja model menggunakan Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), dan Mean Absolute Percentage Error (MAPE), dihasilkan bahwa model Hybrid Prophet–BiLSTM memberikan performa prediksi yang lebih baik dibandingkan model Prophet dan BiLSTM secara individual, khususnya pada data uji. Peramalan iuran JKP pada periode September 2025 hingga Agustus 2026 menunjukkan pola musiman yang konsisten dengan tren historis. Temuan ini menunjukkan bahwa pendekatan Hybrid Prophet–BiLSTM dengan pembobotan LOWE dalam konteks peramalan iuran JKP, yang memberikan alternatif metode peramalan yang lebih adaptif dan akurat bagi pengambilan keputusan strategis BPJS Ketenagakerjaan.
Downloads
References
Almazrouee, Abdulla I., Abdullah M. Almeshal, Abdulrahman S. Almutairi, Mohammad R. Alenezi, dan Saleh N. Alhajeri. 2020. "Long-Term Forecasting of Electrical Loads in Kuwait Using Prophet and Holt–Winters Models." Applied Sciences 10(16):5627. doi: 10.3390/app10165627.
Althelaya, Khaled A., El-Sayed M. El-Alfy, dan Salahadin Mohammed. 2018. "Stock Market Forecast Using Multivariate Analysis with Bidirectional and Stacked (LSTM, GRU)." Dalam 2018 21st Saudi Computer Society National Computer Conference (NCC), 1–7. doi: 10.1109/NCG.2018.8593076.
Arslan, Sedar. 2022. “A hybrid forecasting model using LSTM and Prophet for energy consumption with decomposition of time series data.” PeerJ Computer Science 8: e1001.
Bates, Stephen, Trevor Hastie, dan Robert Tibshirani. 2024. "Cross-Validation: What Does It Estimate and How Well Does It Do It?" Journal of the American Statistical Association 119(546):1434–1445. doi: https://doi.org/10.1080/01621459.2023.2197686.
Bergmeir, Christoph, dan José M. Benítez. 2012. "On the use of cross-validation for time series predictor evaluation." Information Sciences 191:192–213. doi: 10.1016/j.ins.2011.12.028.
Cerqueira, Vítor, Luís Torgo, dan Igor Mozetič. 2020. "Evaluating forecasting performance with cross-validation." International Journal of Forecasting 36(2):413–431. doi: 10.1016/j.ijforecast.2019.05.011.
Chahkotahi, Fatemeh dan Mehdi Khashei. 2022. "Linear Optimal Weighting Estimator (LOWE) for Efficient Parallel Hybridization of Load Forecasts." Journal of Modelling in Management 17(3):1028–1048. doi: https://doi.org/10.1108/JM2-05-2021-0116.
Choubey, Mohit, Rahul Kumar Chaurasiya, dan J. S. Yadav. 2025. "Predicting Electrical Load Demands Using Neural Prophet-Based Forecasting Model." SN Computer Science 6(1):46. doi: 10.1007/s42979-024-03587-6.
Claesen, Marc, dan Bart De Moor. 2015. "Hyperparameter Search in Machine Learning." arXiv. doi: 10.48550/arXiv.1502.02127.
Ghojogh, Benyamin, dan Ali Ghodsi. 2023. “Recurrent Neural Networks and Long Short-Term Memory Networks: Tutorial and Survey.” arXiv. http://arxiv.org/abs/2304.11461.
Goodfellow, Ian, Yoshua Bengio, dan Aaron Courville. 2016. Deep Learning. Cambridge, MA: MIT Press.
Kenyi, Manzu Gerald Simon dan Kayoko Yamamoto. 2024. “A hybrid SARIMA-Prophet model for predicting historical streamflow time-series of the Sobat River in South Sudan.” Discovered Applied Science 6 (457). https://doi.org/10.1007/s42452-024-06083-x.
Kementerian Ketenagakerjaan Republik Indonesia. 2024. Kumpulan Data - Upah Minimum Kabupaten/Kota Menurut Provinsi. Diakses 13 Februari 2025, dari situs resmi Satu Data Kemnaker.
Kementerian Ketenagakerjaan Republik Indonesia. 2025. Kumpulan Data - Data Angkatan Kerja, Penduduk Bekerja, dan Pengangguran Menurut Provinsi. Diakses 13 Februari 2025, dari situs resmi Satu Data Kemnaker.
Kwarteng, Samuel Baffoe dan Poguda Aleksey Andreevich. 2024. "Comparative Analysis of ARIMA, SARIMA and Prophet Model in Forecasting." Research & Development 5(4):110–120. doi: 10.11648/j.rd.20240504.13.
Martínez, Francisco, Francisco Charte, Francisco A. Frías, dan Antonio J. Rivera. 2018. "Hybridizing Time Series Forecasting Models: A Review." Progress in Artificial Intelligence 7(3):161–174. doi: 10.1007/s40009-018-0275-5.
Menculini, Lorenzo, Andrea Marini, Massimiliano Proietti, Alberto Garinei, Alessio Bozza, Cecilia Moretti, dan Marcello Marconi. 2021. "Comparing Prophet and Deep Learning to ARIMA in Forecasting Wholesale Food Prices." Forecasting 3(3):644–662. doi: 10.3390/forecast3030040.
Papastefanopoulos, Vasilis, Pantelis Linardatos, dan Sotiris Kotsiantis. 2020. "COVID-19: A Comparison of Time Series Methods to Forecast Percentage of Active Cases per Population." Applied Sciences 10(11):3880. doi: 10.3390/app10113880.
Pavitha, N. dan Shounak Sugave. 2023. "Optimizing Machine Learning Models: An Adaptive Hyperparameter Tuning Approach." International Journal of Intelligent Systems and Applications in Engineering 11(4):344–354. https://ijisae.org/index.php/IJISAE/article/view/3532.
Prahutama, Alan, Tiani Wahyu Utami, and Hasbi Yasin. 2014. “Prediksi Harga Saham Menggunakan Support Vector Regression Dengan Algoritma Grid Search.” Media Statistika 7(1):29–35. doi: https://doi.org/10.14710/medstat.7.1.29-35.
Republik Indonesia. 2025. Peraturan Pemerintah Nomor 6 Tahun 2025 tentang Perubahan atas Peraturan Pemerintah Nomor 37 Tahun 2021 tentang Penyelenggaraan Program Jaminan Kehilangan Pekerjaan. Jakarta: Sekretariat Negara.
Samal, K. Krishna Rani, Korra Sathya Babu, Santosh Kumar Das, dan Abhirup Acharya. 2019. "Time Series based Air Pollution Forecasting using SARIMA and Prophet Model." Proceedings of the 2019 International Conference on Information Technology and Computer Communications (ITCC '19): 80-85. Singapore: ACM. doi: 10.1145/3355402.3355417.
Schuster, M., dan K. K. Paliwal. 1997. “Bidirectional recurrent neural networks.” IEEE Transactions on Signal Processing 45(11):2673–2681.
Shakeel, Asim, Daotong Chong, dan Jinshi Wang. 2023. "Load Forecasting of District Heating System Based on Improved FB-Prophet Model." Energy 278:127637. doi: 10.1016/j.energy.2023.127637.
Shiri, Farhad Mortezapour, Thinagaran Perumal, Norwati Mustapha, dan Raihani Mohamed. 2023. "A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU." arXiv. doi: 10.48550/arXiv.2305.17646.
Siami-Namini, Sima, Neda Tavakoli, dan Akbar Siami Namin. 2019. "The Performance of LSTM and BiLSTM in Forecasting Time Series." 2019 IEEE International Conference on Big Data (Big Data): 4385-4392. doi: 10.1109/BigData47094.2019.9005997.
Taylor, Sean J., dan Benjamin Letham. 2018. "Forecasting at Scale." The American Statistician 72(1):37–45. doi: 10.1080/00031305.2017.1380080.
Yan, Weizheng, Han Zhang, Jing Sui, dan Dinggang Shen. 2018. "Deep Chronnectome Learning via Full Bidirectional Long Short-Term Memory Networks for MCI Diagnosis." Medical Image Computing and Computer Assisted Intervention 249–257. doi: 10.1007/978-3-030-00931-1_29.
Yang, Li, dan Abdallah Shami. 2020. "On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice." Neurocomputing 415:295–316. doi: 10.1016/j.neucom.2020.07.061.
Yenido˘ gan, I., C¸ayir, A., et al. (2018). Bitcoin forecasting using ARIMA and Prophet. In 2018 3rd International Conference on Computer Science and Engineering (UBMK), 621–624.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Jurnal Jamsostek
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
