Efektivitas Penggabungan Data Lintas Provinsi dan Augmentasi TimeGAN pada Prediksi Harga Beras Berbasis LSTM
- Sinta Dwi Lestari Universitas Teknologi Yogyakarta, Daerah Istimewa Yogyakarta, Indonesia
-
Umar Zaky
*
Universitas Teknologi Yogyakarta, Daerah Istimewa Yogyakarta,
Indonesia
(*) Corresponding Author
Abstract
Rice price fluctuations in each province are difficult to predict, although accurate forecasts are needed to anticipate price shocks, while the multivariate data available for several provinces are often short. This study compares two ways of addressing this limitation in a Long Short-Term Memory (LSTM) model: pooling data from three provinces (East Java, Central Java, and West Java) into a single model, and adding synthetic data from a Time-series Generative Adversarial Network (TimeGAN). Monthly data (March 2024 to March 2026) from four sources (weather, rice prices, food reserve stocks, and exchange rates) yielded 25 observations per province. The 84 scenarios under three training conditions (no augmentation, 50%, and 100% augmentation) made 252 experiments, assessed with MAPE, RMSE, and MAE. The pooled model K7 was more accurate than local models in all three provinces. Without augmentation, mean MAPE fell from 2.056% to 1.258%, RMSE from IDR 326.777/kg to IDR 223.018/kg, and MAE from IDR 306.063/kg to IDR 187.795/kg. In contrast, TimeGAN augmentation produced no detectable improvement, and at 100% it tended to raise the pooled models’ MAPE from 1.541% to 1.710%. The synthetic data were easily distinguishable from the real data (mean discriminative score 0.893). For food price monitoring in regions with short data, collecting real data from other provinces appears more promising than building synthetic data, so price-forecasting systems can prioritize pooling data across provinces before adding generative models.
Downloads
References
AlSalehy, A. S., & Bailey, M. (2025). Improving time series data quality: Identifying outliers and handling missing values in a multilocation gas and weather dataset. Smart Cities, 8(3), 82. https://doi.org/10.3390/smartcities8030082
Ashari, Y., & Suhendar, A. (2024). Implementasi algoritma long short-term memory (LSTM) untuk memprediksi harga beras di Jawa Tengah berdasarkan cuaca. Djtechno: Jurnal Teknologi Informasi, 5(3), 624–636. https://doi.org/10.46576/djtechno.v5i3.5136
Benidis, K., Rangapuram, S. S., Flunkert, V., Wang, Y., Maddix, D., Turkmen, C., Gasthaus, J., Bohlke-Schneider, M., Salinas, D., Stella, L., Aubet, F.-X., Callot, L., & Januschowski, T. (2022). Deep learning for time series forecasting: Tutorial and literature survey. ACM Computing Surveys, 55(6), 1–36. https://doi.org/10.1145/3533382
Damaliana, A. T., Tyas, S. W., Muhaimin, A., Trimono, Wara, S. S. M., & Idhom, M. (2025). Deep stacking ensemble with stacked LSTM and SVR for analysis and forecasting: A case study of rice price in East Java. 2025 IEEE 11th Information Technology International Seminar (ITIS), 356–361. https://doi.org/10.1109/ITIS67966.2025.11309025
Hewamalage, H., Ackermann, K., & Bergmeir, C. (2023). Forecast evaluation for data scientists: Common pitfalls and best practices. Data Mining and Knowledge Discovery, 37(2), 788–832. https://doi.org/10.1007/s10618-022-00894-5
Hewamalage, H., Bergmeir, C., & Bandara, K. (2022). Global models for time series forecasting: A simulation study. Pattern Recognition, 124, 108441. https://doi.org/10.1016/j.patcog.2021.108441
Hidayat, R., & Wibisonya, I. (2024). Rice price prediction with long short-term memory (LSTM) neural network. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 8(5), 658–664. https://doi.org/10.29207/resti.v8i5.6041
James, G., Witten, D., Hastie, T., Tibshirani, R., & Taylor, J. (2023). An introduction to statistical learning: With applications in Python. Springer. https://doi.org/10.1007/978-3-031-38747-0
Jiwandono, D., & Girsang, A. S. (2025). Strategic food commodity price forecasting using LSTM and SARIMAX: A case study of Bandung City and Bogor Regency, Indonesia. 2025 13th International Conference on Orange Technology (ICOT), 1–7. https://doi.org/10.1109/ICOT68409.2025.11425334
Khand, K., & Senay, G. B. (2024). Evaluation of streamflow predictions from LSTM models in water- and energy-limited regions in the United States. Machine Learning with Applications, 16, 100551. https://doi.org/10.1016/j.mlwa.2024.100551
Khatun, A., Nisha, M. N., Chatterjee, S., & Sridhar, V. (2024). A novel insight on input variable and time lag selection in daily streamflow forecasting using deep learning models. Environmental Modelling & Software, 179, 106126. https://doi.org/10.1016/j.envsoft.2024.106126
Li, J., Zhang, X., Hu, Q., Zhang, F., Gaidai, O., & Chen, L. (2024). Data augmentation technique based on improved time-series generative adversarial networks for power load forecasting in recirculating aquaculture systems. Sustainability, 16(23), 10721. https://doi.org/10.3390/su162310721
Liu, J., & Xu, Y. (2022). T-Friedman test: A new statistical test for multiple comparison with an adjustable conservativeness measure. International Journal of Computational Intelligence Systems, 15(1), 29. https://doi.org/10.1007/s44196-022-00083-8
Mahjoub, S., Chrifi-Alaoui, L., Marhic, B., & Delahoche, L. (2022). Predicting energy consumption using LSTM, multi-layer GRU and Drop-GRU neural networks. Sensors, 22(11), 4062. https://doi.org/10.3390/s22114062
Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2022). M5 accuracy competition: Results, findings, and conclusions. International Journal of Forecasting, 38(4), 1346–1364. https://doi.org/10.1016/j.ijforecast.2021.11.013
Murphy, K. P. (2023). Probabilistic machine learning: Advanced topics. MIT Press.
Nakatsu, R. T. (2023). Validation of machine learning ridge regression models using Monte Carlo, bootstrap, and variations in cross-validation. Journal of Intelligent Systems, 32(1), 20220224. https://doi.org/10.1515/jisys-2022-0224
Novita, D., Suharno, S., Nurmalina, R., & Nuryantoro, N. (2024). The effect of rice price on the Indonesian inflation in a new institutional economic perspective. Agrisocionomics: Jurnal Sosial Ekonomi Pertanian, 8(2), 621–636. https://doi.org/10.14710/agrisocionomics.v8i2.24146
Okere, E. E., & Balyan, V. (2025). A deep learning-based prediction and forecasting of tomato prices for the Cape Town fresh produce market: A model comparative analysis. Forecasting, 7(2), 19. https://doi.org/10.3390/forecast7020019
Setiyani, L., Handayani, H. H., & Geraldine, W. A. (2023). Rice price forecasting using GridSearchCV and LSTM. 2023 International Conference on Modeling & E-Information Research, Artificial Learning and Digital Applications (ICMERALDA), 127–131. https://doi.org/10.1109/ICMERALDA60125.2023.10458179
Tai, C.-Y., Wang, W.-J., & Huang, Y.-M. (2023). Using time-series generative adversarial networks to synthesize sensing data for pest incidence forecasting on sustainable agriculture. Sustainability, 15(10), 7834. https://doi.org/10.3390/su15107834
Tamayo-Urgilés, D., Sanchez-Gordon, S., Valdivieso Caraguay, Á. L., & Hernández-Álvarez, M. (2024). GAN-based generation of synthetic data for vehicle driving events. Applied Sciences, 14(20), 9269. https://doi.org/10.3390/app14209269
Tang, P., Li, Z., Wang, X., Liu, X., & Mou, P. (2025). Time series data augmentation for energy consumption data based on improved TimeGAN. Sensors, 25(2), 493. https://doi.org/10.3390/s25020493
van Zyl, J.-P., & Engelbrecht, A. P. (2025). Analysis of classification metric behaviour under class imbalance. Egyptian Informatics Journal, 31, 100711. https://doi.org/10.1016/j.eij.2025.100711
Weng, P., Tian, Y., Liu, Y., & Zheng, Y. (2023). Time-series generative adversarial networks for flood forecasting. Journal of Hydrology, 622, 129702. https://doi.org/10.1016/j.jhydrol.2023.129702
Zhang, Y., Zhou, Z., Liu, J., & Yuan, J. (2022). Data augmentation for improving heating load prediction of heating substation based on TimeGAN. Energy, 260, 124919. https://doi.org/10.1016/j.energy.2022.124919
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Efektivitas Penggabungan Data Lintas Provinsi dan Augmentasi TimeGAN pada Prediksi Harga Beras Berbasis LSTM
Copyright (c) 2026 Sinta Dwi Lestari, Umar Zaky
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International 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 (Refer to The Effect of Open Access).
