Heterogeneous Stacking Ensemble with SMOTE-Based Oversampling for Agricultural Commodity Price Prediction under Extreme Class Imbalance
DOI:
https://doi.org/10.29207/resti.v10i5.8065Keywords:
agricultural commodity price prediction, deep learning, LightGBM, SMOTE, stacking ensembleAbstract
Predicting agricultural commodity prices is vital for food security and market stability, but price data is highly non-linear, high-cardinality, and severely imbalanced, rendering conventional accuracy metrics misleading. This study proposes a heterogeneous stacking ensemble of LightGBM, XGBoost, and Random Forest base learners with a LightGBM meta-learner, evaluated against five BorderlineSMOTE oversampling variants and four ensemble configurations under a 282:1 class imbalance. A controlled ablation across six configurations — including a new factorial design that isolates the contributions of oversampling and an MLP base learner — demonstrates that performance is driven by the stacking architecture rather than by synthetic oversampling or deep learning components. The ensemble without oversampling achieves MCC = 0.9509 and AUC-OvR = 0.9908 on the held-out test set, while the addition of an MLP base learner yields no consistent improvement (|ΔMCC| < 0.008 across both SMOTE and no-SMOTE conditions). These findings identify cost-sensitive heterogeneous stacking as an effective and computationally tractable strategy for highly imbalanced tabular agricultural data, and establish that synthetic oversampling and MLP-based components are unnecessary under these conditions.Downloads
References
[1] Y. Thakre, I. Javeri, J. Sajwani, J. Kulkarni, and S. Maskare, “Commodity Price Prediction Using Machine Learning: Insights, Challenges, and Prospect,” in 2025 International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence, RAEEUCCI 2025, 2025. doi: 10.1109/RAEEUCCI63961.2025.11048306.
[2] R. Ragunath and R. Rathipriya, “Forecasting Agriculture Commodity Price Trend using Novel Competitive Ensemble Regression Model,” International Journal of Information Technology and Computer Science, vol. 17, no. 3, 2025, doi: 10.5815/ijitcs.2025.03.07.
[3] T. Zhang and Z. Tang, “Agricultural commodity futures prices prediction based on a new hybrid forecasting model combining quadratic decomposition technology and LSTM model,” Front. Sustain. Food Syst., vol. 8, 2024, doi: 10.3389/fsufs.2024.1334098.
[4] H. A. Putra et al., “Understanding Short-Term and Long-Term Price Fluctuations of Main Staple Food Commodities in Aceh Province, Indonesia: An ARDL Investigation,” Ekonomikalia Journal of Economics, vol. 1, no. 1, 2023, doi: 10.60084/eje.v1i1.50.
[5] E. M. Amrouk, S. C. Grosche, and T. Heckelei, “Interdependence between cash crop and staple food international prices across periods of varying financial market stress,” Appl. Econ., vol. 52, no. 4, 2020, doi: 10.1080/00036846.2019.1645281.
[6] D. Lederman and G. Porto, “The price is not always right: On the impacts of commodity prices on households (and countries),” World Bank Research Observer, vol. 31, no. 1, 2016, doi: 10.1093/wbro/lkv013.
[7] N.-Q. Tran et al., “Predicting Agricultural Commodities Prices with Machine Learning: A Review of Current Research,” School of Science, Engineering, and Technology, RMIT University Vietnam, vol. 1, no. 1, 2023.
[8] F. Sun, X. Meng, Y. Zhang, Y. Wang, H. Jiang, and P. Liu, “Agricultural Product Price Forecasting Methods: A Review,” 2023. doi: 10.3390/agriculture13091671.
[9] S. Dutt, P. N. Kulkarni, S. Akilan, R. Mishra, P. Khetan, and A. Bhadora, “AGRICULTURAL PRICE PREDICTION THROUGH ARTIFICIAL INTELLIGENCE,” International Journal of Development Research, vol. 14, no. 3, 2024.
[10] S. Bunrit, N. Kerdprasop, and K. Kerdprasop, “Multiresolution analysis based on wavelet transform for commodity prices time series forecasting,” Int. J. Mach. Learn. Comput., vol. 8, no. 2, 2018, doi: 10.18178/ijmlc.2018.8.2.683.
[11] D. Zhang, S. Chen, L. Liwen, and Q. Xia, “Forecasting Agricultural Commodity Prices Using Model Selection Framework with Time Series Features and Forecast Horizons,” IEEE Access, vol. 8, 2020, doi: 10.1109/ACCESS.2020.2971591.
[12] K. Lee and S. Park, “ARIMA-GARCH for commodity price forecasting: Gold markets,” J. Int. Money Finance, vol. 139, no. 1, 2024.
[13] M. P. Yadav, V. Sehgal, D. Ratra, and A. Wajid, “Forecasting the energy commodities: an evidence of ARIMA and intervention analysis,” International Journal of Monetary Economics and Finance, vol. 16, no. 6, 2024, doi: 10.1504/IJMEF.2023.136086.
[14] M. Mujiyanto, S. Nurindahsari, and R. N. Izza, “Comparison of Linear Regression, ARIMA, Simple Exponential Smoothing, Hybrid ARIMA-LSTM, and EWMA in Forecasting Commodity Prices,” Telematika, vol. 17, no. 2, 2024, doi: 10.35671/telematika.v17i2.2932.
[15] S. P. Das and S. Padhy, “A novel hybrid model using teaching–learning-based optimization and a support vector machine for commodity futures index forecasting,” International Journal of Machine Learning and Cybernetics, vol. 9, no. 1, 2018, doi: 10.1007/S13042-015-0359-0.
[16] S. A. Harjanto, S. Sa’adah, and G. S. Wulandari, “Export Commodity Price Forecasting in Indonesia Using Decision Tree, Random Forest, and Long Short-Term Memory,” Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, vol. 8, no. 4, 2023, doi: 10.26555/jiteki.v8i4.25242.
[17] M. Fałdziński, P. Fiszeder, and W. Orzeszko, “Forecasting volatility of energy commodities: Comparison of garch models with support vector regression,” Energies (Basel)., vol. 14, no. 1, 2021, doi: 10.3390/en14010006.
[18] R. L. Manogna, V. Dharmaji, and S. Sarang, “Enhancing agricultural commodity price forecasting with deep learning,” Sci. Rep., vol. 15, no. 1, 2025, doi: 10.1038/s41598-025-05103-z.
[19] H. Ben Ameur, S. Boubaker, Z. Ftiti, W. Louhichi, and K. Tissaoui, “Forecasting commodity prices: empirical evidence using deep learning tools,” Ann. Oper. Res., vol. 339, no. 1–2, 2024, doi: 10.1007/s10479-022-05076-6.
[20] Y. Siagian, J. Hutahaean, and N. Mulyani, “Stacking Ensemble with SMOTE for Robust Agricultural Commodity Price Prediction under Imbalanced Data,” Journal of Applied Data Sciences, vol. 6, no. 4, 2025, doi: 10.47738/jads.v6i4.916.
[21] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic Minority Over-sampling Technique,” Journal of Artificial Intelligence Research, vol. 16, pp. 321–357, Jun. 2002, doi: 10.1613/jair.953.
[22] H. Al Majzoub, I. Elgedawy, Ö. Akaydın, and M. Köse Ulukök, “HCAB-SMOTE: A Hybrid Clustered Affinitive Borderline SMOTE Approach for Imbalanced Data Binary Classification,” Arab. J. Sci. Eng., vol. 45, no. 4, 2020, doi: 10.1007/s13369-019-04336-1.
[23] J. Yang and J. Guan, “A Heart Disease Prediction Model Based on Feature Optimization and Smote-Xgboost Algorithm,” Information, vol. 13, no. 10, p. 475, Oct. 2022, doi: 10.3390/info13100475.
[24] Y. Sun et al., “Borderline SMOTE Algorithm and Feature Selection‐Based Network Anomalies Detection Strategy,” Energies (Basel)., vol. 15, no. 13, 2022, doi: 10.3390/en15134751.
[25] J. Brandt and E. Lanzén, “A Comparative Review of SMOTE and ADASYN in Imbalanced Data Classification,” 2021, 2020.
[26] Z. Wang, C. Wu, K. Zheng, X. Niu, and X. Wang, “SMOTETomek-Based Resampling for Personality Recognition,” IEEE Access, vol. 7, 2019, doi: 10.1109/ACCESS.2019.2940061.
[27] G. Husain et al., “SMOTE vs. SMOTEENN: A Study on the Performance of Resampling Algorithms for Addressing Class Imbalance in Regression Models,” Algorithms, vol. 18, no. 1, 2025, doi: 10.3390/a18010037.
[28] D. H. Wolpert, “Stacked generalization,” Neural Networks, vol. 5, no. 2, 1992, doi: 10.1016/S0893-6080(05)80023-1.
[29] A. I. Naimi and L. B. Balzer, “Stacked generalization: an introduction to super learning,” Eur. J. Epidemiol., vol. 33, no. 5, 2018, doi: 10.1007/s10654-018-0390-z.
[30] X. Qiao, X. Tian, X. Zhang, Y. Wang, and S. Hou, “RDES-stack model—A study on an improved energy consumption forecasting model,” Sustainable Energy Technologies and Assessments, vol. 84, 2025, doi: 10.1016/j.seta.2025.104683.
[31] H. Talebi, A. K. Bardsiri, and V. K. Bardsiri, “Developing a hybrid machine learning model for employee turnover prediction: Integrating LightGBM and genetic algorithms,” Journal of Open Innovation: Technology, Market, and Complexity, vol. 11, no. 2, 2025, doi: 10.1016/j.joitmc.2025.100557.
[32] X. Zhao, Y. Liu, and Q. Zhao, “Cost Harmonization LightGBM-Based Stock Market Prediction,” IEEE Access, vol. 11, 2023, doi: 10.1109/ACCESS.2023.3318478.
[33] S. Hakkal and A. A. Lahcen, “XGBoost To Enhance Learner Performance Prediction,” Computers and Education: Artificial Intelligence, vol. 7, 2024, doi: 10.1016/j.caeai.2024.100254.
[34] H. Oukhouya, H. Kadiri, K. El Himdi, and R. Guerbaz, “Forecasting International Stock Market Trends: XGBoost, LSTM, LSTM-XGBoost, And Backtesting XGBoost Models,” Statistics, Optimization and Information Computing, vol. 12, no. 1, 2024, doi: 10.19139/soic-2310-5070-1822.
[35] H. A. Salman, A. Kalakech, and A. Steiti, “Random Forest Algorithm Overview,” 2024. doi: 10.58496/BJML/2024/007.
[36] J. Lyu, H. Shi, J. Zhang, and J. Norvilitis, “Prediction model for suicide based on back propagation neural network and multilayer perceptron,” Front. Neuroinform., vol. 16, 2022, doi: 10.3389/fninf.2022.961588.
[37] F. Murtagh, “Multilayer perceptrons for classification and regression,” Neurocomputing, vol. 2, no. 5–6, 1991, doi: 10.1016/0925-2312(91)90023-5.
[38] D. Chicco and G. Jurman, “The Matthews correlation coefficient (MCC) should replace the ROC AUC as the standard metric for assessing binary classification,” BioData Min., vol. 16, no. 1, 2023, doi: 10.1186/s13040-023-00322-4.
[39] D. Chicco and G. Jurman, “The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation,” BMC Genomics, vol. 21, no. 1, 2020, doi: 10.1186/s12864-019-6413-7.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;
