Comparative Analysis of LSTM and 1D-CNN for Food Commodity Price Prediction in East Java
DOI:
https://doi.org/10.30871/jaic.v10i2.12511Keywords:
Convolutional Neural Network, East Java, Food Price Prediction, Long Short-Term MemoryAbstract
Accurate food price predictions are crucial for maintaining market stability and developing policy strategies in new food areas. This study aims to compare two deep learning models, namely Long Short-Term Memory (LSTM) and 1D Convolutional Neural Network (CNN-1D), in predicting monthly prices of 6 food commodities in East Java. Price data from January 2020 to July 2025 were cleaned before being used for model training. The evaluation results show that there is no single best model. Rather, performance depends heavily on the data characteristics of each commodity. The LSTM model provides the lowest MAPE for Medium Rice Commodities (1.05%), Premium Rice (1.85%), Dry Milled Grain (4.32%), Harvested Dry Grain (2.40%), and Dry Shelled Corn (1.27%), indicating its ability to identify long-term patterns and seasonal fluctuations. Meanwhile, for Soybeans, CNN-1D is more accurate, with a MAPE of 0.79%, because it captures short-term fluctuations that often occur. The implication of this research is the importance of a commodity-specific approach in selecting a price prediction model. The resulting 12-month price forecasts can serve as a reference for policymakers in planning regional food stabilization.
Downloads
References
[1] Y. R. Noor and Universitas, “Pengaruh Volatilitas Harga Terhadap Produksi Jagung Pakan Di Provinsi Jawa Timur,” 2021.
[2] E. Triwidia, I. Nuraini, A. Boedirochminarni, and M. Firmansyah, “‘ Produktivitas Padi , Indeks Harga yang Dibayar Petani dan Produksi Padi terhadap Kesejahteraan Petani di Indonesia ,’” vol. 8, no. 2, pp. 213–223, 2024.
[3] F. D. Isnaini et al., “Penerapan Holt-Winters Untuk Peramalan Harga,” vol. 12, no. 3, 2024.
[4] Intan Mega Puspita, “Prediksi Harga Beras Ir-64 Iii Menggunakan Algoritma Long Short Term Memory (LSTM),” Progr. Stud. Tek. Inform. Fak. ILMU Komput. Univ. Mercu Buana, 2021.
[5] M. J. Vikri et al., “Rice Quality Identification For Indonesian Food Standards Based On Electronic Nose Berdasarkan Standar Pangan Indonesia Berbasis,” vol. 10, no. 1, 2025.
[6] C. Xia, “Comparative Analysis of ARIMA and LSTM Models for Agricultural Product Price Forecasting,” vol. 85, pp. 1032–1040, 2024.
[7] D. Engineer, I. Researcher, and K. L. Educational, “Advancing Crop Yield Prediction Through Machine And Deep Learning For Next-Gen Farming,” vol. 102, no. 22, pp. 8300–8311, 2024.
[8] J. Cahyani, S. Mujahidin, and T. Palyus, “Implementasi Metode Long Short Term Memory ( LSTM ) untuk Memprediksi Harga Bahan Pokok Nasional,” vol. 11, no. 2, pp. 346–357, 2023, doi: 10.26418/justin.v11i2.57395.
[9] C. Elyca et al., “Computationally Efficient Single Layer Transformer Convolutional Encoder for Accurate Price Prediction of Agriculture Commodities,” IEEE Access, vol. 13, no. April, pp. 82144–82159, 2025, doi: 10.1109/ACCESS.2025.3567903.
[10] A. I. E. Nensi, W. Pangesti, N. Syukri, and K. A. Notodiputro, “Implementing LSTM-Based Deep Learning for Forecasting Food Commodity Prices with High Volatility : A Case Study in East Java Province,” pp. 1032–1041.
[11] P. Studi, M. Statistika, D. A. N. Sains, S. S. Data, and D. A. N. Informatika, “Kajian Model Peramalan Tiga Harga Komoditas Pangan Untuk 34 Ibu Kota Provinsi Dengan Pendekatan Multivariate Time Series,” 2025.
[12] S. Wira and A. Utomo, “Artificial Neural Network Untuk Memprediksi Produksi Tanaman Menggunakan Metode Backpropagation Di Dinas Pertanian Dan Pangan Kabupaten Magelang Provinsi Jawa Tengah (Studi Pada Produksi Tamanan Cabai),” 2025.
[13] M. Lim, T. Handayani, T. Informatika, F. T. Informasi, and U. Tarumanagara, “Penerapan lstm dan gru untuk prediksi harga cabai merah di kota jawa timur,” vol. 13, no. 2, 2025.
[14] J. R. B. Nadiya Auliya Nur Rohmah, M. Jauhar Vikri, Sistem Pendeteksi Kualitas Tanaman Lidah Buaya Berbasis Citra Digital Menggunakan Metode Convolutional Neural Network (Cnn). Program Studi S1 Teknik Informatika Fakultas Sains Dan Teknologi Universitas Nahdlatul Ulama Sunan Giri 202, 2025.
[15] A. Thaker and L. H. Chan, “Forecasting Agriculture Commodity Futures Prices with Convolutional Neural Networks with Application to Wheat Futures,” 2024.
[16] K. Sun, Q. Yao, and Y. Li, “A novel agricultural commodity price prediction model integrating deep learning and enhanced swarm intelligence algorithm,” 2025, doi: 10.1371/journal.pone.0337103.
[17] T. Zhao, G. Chen, S. Suraphee, and T. Phoophiwfa, “A hybrid TCN-XGBoost model for agricultural product market price forecasting,” pp. 1–31, 2025, doi: 10.1371/journal.pone.0322496.
[18] M. A. Setyadji, A. Faqih, and Y. A. Wijaya, “Peramalan Harga Komoditas Beras Di Kalimantan Timur Menggunakan Algoritma Neural Network,” vol. 7, no. 1, pp. 320–324, 2023.
[19] Raka, “Harga Pertanian Jawa Timur,” Kaggle. [Online]. Available: https://www.kaggle.com/datasets/rakafal/harga-pertanian-jawa-timur
[20] M. R. Pradana, W. Witanti, and A. Komarudin, “JURNAL LOCUS : Penelitian & Pengabdian Prediksi Tingkat Keparahan Diabetes Melitus Menggunakan Support Vector Machine ( SVM ) dengan Kernel Polinomial dan RBF,” vol. 4, no. 8, pp. 7521–7533, 2025.
[21] D. Oleh et al., “Untuk Prediksi Harga Saham Menggunakan Alpha Vantage Api Untuk Prediksi Harga Saham Menggunakan,” 2025.
[22] T. W. Septiarini, M. D. P. Martinasari, and E. Pariyanti, “The Impact of Training-Testing Proportion on Forecasting Accuracy : A Case of Agricultural Export in Indonesia”.
[23] D. T. Varanpong Suthiponpisal, “A Comparative Evaluation of Noise Reduction Versus Data Normalization Techniques in Stock Market Prediction Using Transformer Models,” 2024 9th Int. Conf. Inf. Technol., 2024, [Online]. Available: https://ieeexplore.ieee.org/document/10810587/metrics#metrics
[24] P. N. Lidia and F. Ariyanto, “Penerapan Algoritma LSTM Untuk Prediksi Harga Bahan Pangan Di Pamekasan,” vol. 11, no. 1, pp. 382–390, 2025.
[25] A. Nurhidayat, W. A. Arrosyid, and R. Samsinar, “Prediksi Tumor Otak Menggunakan Metode Convolutional Neural Network ( CNN ) dan Algoritma Decision Tree,” vol. 4, pp. 660–666, 2025.
[26] I. J. Informatika et al., “Prediksi Harga Emas Indonesia Menggunakan Model CNN-LSTM,” vol. 27, no. April, pp. 131–138, 2025, doi: 10.23969/infomatek.v27i1.24417.
[27] R. N. Silalahi, T. Informatika, F. I. Komputer, U. Dian, and N. Semarang, “Komputika : Jurnal Sistem Komputer Perbandingan Kinerja Metode Linear Regression , LSTM dan GRU untuk Prediksi Harga Penutupan Saham Coca-Cola Performance Comparison Of Linear Regression , LSTM & GRU Methods For Coca-Cola Stock Closing Price Prediction,” vol. 13, 2024, doi: 10.34010/komputika.v13i2.12265.
[28] T. Zhao, G. Chen, S. Suraphee, T. Phoophiwfa, and P. Busababodhin, “Model hibrida TCN-XGBoost untuk peramalan harga pasar produk pertanian,” pp. 1–20, 2025.
[29] H. Rusanto and S. Soekirno, “Performance Comparison of 1D-CNN and LSTM Deep Learning Models for Time Series-Based Electric Power Prediction,” vol. 13, no. 1, pp. 44–56, 2025.
[30] F. Insani and S. Sanjaya, “Implementasi Long Short Term Memory Neural Network Untuk Prediksi Indeks Harga Perdagangan Besar,” 2022.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Lidya Puji Putriawati Ngadirun, Mula Agung Barata, Ifnu Wisma Dwi Prastya
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:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement 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 acknowledgement 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 (See The Effect of Open Access).
