Comparison of SVR Parameter Optimization Using Particle Swarm Optimization (PSO) and Random Search for Rice Harvest Yield Prediction
DOI:
https://doi.org/10.52436/1.jutif.2026.7.3.5509Keywords:
Padi, Particle flock o Roptimization, Agriculture, Support Vector Regression, ProduceAbstract
Rice yield is an important part in a precision agriculture system that can support farmers' decision-making in a more targeted manner. The author's research aims to help farmers and stakeholders in Bambang Village predict crop yields accurately to overcome production fluctuations. Through appropriate efforts and strategies, this technology is expected to improve food security and farmer welfare. The research method uses the Support Vector Regression (SVR) algorithm for the modeling process, with the help of Particle Swarm Optimization (PSO) and Random Search optimization in finding the best parameters. The research dataset includes 1,120 historical data of rice harvests in Bambang Village for the 2022–2023 period tested through 70:30 and 60:40 data sharing scenarios. Model performance is evaluated using the Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and coefficient of determination (R2) metrics. The MAPE metric is used as the main indicator of relative accuracy by measuring the average percentage deviation between predicted values and actual values; a low MAPE value is very significant because it reflects the model has a minimal error rate on a percentage scale, thus providing more precise estimates for farmers. The results showed that both optimization methods successfully identified SVR parameters (C, gamma, epsilon) that followed the data trend. Random Search produced slightly superior R2 performance (reaching 82.20% at a 60:40 ratio), while PSO showed more consistent parameter exploration stability. These findings demonstrate that the integration of machine learning and optimization techniques has great potential in strengthening data-driven agricultural systems to improve food security and farmer welfare.
Downloads
References
F. Esfandiari et al. , “Assistance of MUI Halal Contract and Certification and Education on Halal Product Assurance for Cangloh Beverages in Mergosono, Malang City,” J. Dedik. huh. , vol. 1, no. 2, pp. 87–99, 2021, doi: 10.22219/jdh.v1i2.17607.
EIR Rhofita, “Optimizing Indonesian Agricultural Resources to Support the National Food and Energy Security Program,” J. National Resilience , vol. 28, no. 1, p. 82, 2022, doi: 10.22146/jkn.71642.
ICR Drajana and A. Bode, “Support Vector Machine for Food Crop Production Prediction in Gorontalo Province,” Nusant. English , vol. 4, no. 2, pp. 104–111, 2021, doi: 10.29407/noe.v4i2.16757.
Q. Ayun, S. Kurniawan, and WA Saputro, “The Development of Agricultural Land Conversion in Agrarian Countries,” Vigor J. Agricultural Science. Trop. And Subtrop. , vol. 5, no. 2, pp. 38–44, 2020, doi: 10.31002/vigor.v5i2.3040.
S. Nurul, F. Harahap, J. Nasution, and K. Tambunan, “Rice supplies, rice prices, rice consumption against inflation in Medan city,” vol. 13, no. 02, pp. 625–638, 2024.
A. Basit, “IMPLEMENTATION OF NAIVE BAYES ALGORITHM TO PREDICTE RICE HARVEST RESULTS,” J. Tech. Inform. Kaputama , vol. 4, no. 2, pp. 208–213, 2020.
AAP Jusnawati, Arifin, “Jusnawati, Arifin, Abd.Asis Pata: Contribution of Paddy Production in SIPILU Center Areas (Sidrap, Pinrang, Luwu) to Paddy Production in South Sulawesi,” vol. 12, no. 2, pp. 46–55, 2020.
R. Rustam, S. Rahmatullah, S. Supriyato, and S. Wahyuni, “Application of Data Mining for Predicting Plywood Product Sales at PT Puncak Menara Hijau Mas,” J. Inf. and Computer. , vol. 8, no. 2, pp. 75–86, 2020, doi: 10.35959/jik.v8i2.186.
Mulyawan, R. Subagja, D. Rohman, and DI Efendi, “Implementation of Support Vector Regression for House Price Prediction with Grid Search Optimization,” J. Electron. Comput. Sci. Udayana , vol. 12, no. 3, pp. 687–696, 2024.
MA Adam, HY Chrisnanto, and RF Umbara, “Predicting Financial Patterns in the Indonesian Stock Exchange Stock Market Using the Support Vector Machine for Regression (SVR) Algorithm,” J. Education and Research. Inform. , vol. 10, no. 3, pp. 476–484, 2024.
AM Ahmed, “Scientific Journal of Cihan University – Sulaimaniya,” Sci. J. Cihan Univ. – Sulaimaniya , vol. 6, no. 1, pp. 145–156, 2022.
K. Watanabe and X. Xu, “Particle swarm optimization based on nonlinear crossing strategy with time-varying acceleration coefficient,” Appl. Intell. , vol. 54, no. 13–14, pp. 7229–7277, 2024, doi: 10.1007/s10489-024-05502-1.
D. Pebrianti, H. Kurniawan, L. Bayuaji, and R. Rusdah, “XgBoost Hyper-Parameter Tuning Using Particle Swarm Optimization for Stock Price Forecasting,” J. Ilm. Tech. Elektro Comput. dan Inform. , vol. 9, no. 4, pp. 1179–1195, 2023, doi: 10.26555/jiteki.v9i4.27712.
E. Bayraktar, I. Ekren, and X. Zhang, “Prediction against finite opponents,” J. Mach. Learn. Res. , vol. 22, pp. 1–33, 2021.
MH Rizky, MR Faisal, I. Budiman, D. Kartini, and F. Abadi, “The Effect of Hyperparameter Tuning Using Random Search on Tree-Based Classification Algorithms for Software Defect Prediction,” IJCCS (Indonesian J. Comput. Cybern. Syst. , vol. 18, no. 1, p. 95, 2024, doi: 10.22146/ijccs.90437.
ARM Rom, N. Jamil, and S. Ibrahim, “Multi-objective hyperparameter tuning via random search on deep learning models,” Telkomnika (Telecommunication Comput. Electron. Control. , vol. 22, no. 4, pp. 956–968, 2024, doi: 10.12928/TELKOMNIKA.v22i4.25847.
M. Arifin, W. Widowati, and F. Farikhin, “Hyperparameter Optimization in Machine Learning to Improve Student Academic Performance Prediction,” Ing. des Syst. d'Information , vol. 28, no. 3, pp. 575–582, 2023, doi: 10.18280/isi.280305.
M. Sholeh, U. Lestari, and D. Andayati, “Hyperparameter Optimization Using Grid Search and Random Search to Improve the Performance of Prediction Models with Decision Trees,” J. Ris. Multidisciplinary and Inov. Technol. , vol. 3, no. 03, pp. 453–464, 2025, doi: 10.59653/jimat.v3i03.2025.
SFA Khansa, N. Ulinnuha, and WD Utami, “Optimization of Hyperparameter Tuning of Grid Search and Random Search on Xgboost Algorithm for Parkinson's Disease Classification,” Barekeng , vol. 19, no. 3, pp. 1609–1624, 2025, doi: 10.30598/barekengvol19iss3pp1609-1624.
S. Pratista, A. Nazir, I. Iskandar, E. Budianita, and I. Afrianty, “Comparison of Drug Use Prediction Techniques Using Simple Linear Regression Algorithms and Support Vector Regression,” vol. 5, no. 2, August 2023, doi: 10.47065/bits.v5i2.4260.
T. Aprilia, APPLICATION OF SUPPORT VECTOR REGRESSION (SVR) AND PARTICLE SWARM OPTIMIZATION (PSO) METHODS FOR FORECASTING RICE PRODUCTION RESULTS .
S. Erçel and S. Akyol, “Impact of Data Preprocessing Techniques on the Performance of Machine Learning Models for Drought Prediction,” Acadlore Trans. AI Mach. Learn. , vol. 4, no. 1, pp. 14–24, 2025, doi: 10.56578/ataiml040102.
BM Akbar, AT Akbar, and R. Husaini, “Sentiment and Emotion Analysis of Sinovac Vaccine on Twitter using Naive Bayes and Valence Shifter,” J. Integrated Technol. , vol. 7, no. 2, pp. 83–92, 2021, doi: 10.54914/jtt.v7i2.433.
K. Purohit, “Separation of Data Cleaning Concepts from EDA,” Int. J. Data Sci. Anal. , vol. 7, no. 3, p. 89, 2021, doi: 10.11648/j.ijdsa.20210703.16.
S. Saadah and H. Salsabila, “Bitcoin Price Prediction Using the Random Forest Method,” J. Comput. Terap. , vol. 7, no. 1, pp. 24–32, 2021, doi: 10.35143/jkt.v7i1.4618.
C. Okpara, C. Edokwe, G. Ioannidis, A. Papaioannou, J.D. Adachi, and L. Thabane, “Reporting and handling of missing data in longitudinal studies of older adults remains suboptimal: a methodological survey of geriatrics journals,” BMC Med. Res. Methodol. , vol. 22, no. 1, pp. 1–9, 2022, doi: 10.1186/s12874-022-01605-w.
Z. Rais, “Support Vector Regression (SVR) Analysis with Kernel Radial Basis Function (Rbf) to Predict Inflation Rate in Indonesia,” VARIANCE J. Stat. Appl. Teach. Res. , vol. 4, no. 1, pp. 30–38, 2022, doi: 10.35580/variansiunm13.
N. Aldhafferi, “Android Malware Detection Using Support Vector Regression for Dynamic Feature Analysis,” Inf. , vol. 15, no. 10, 2024, doi: 10.3390/info15100658.
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Narlin Yumeivia, Farid Wajidi, Wawan Firgiawan
This work is licensed under a Creative Commons Attribution 4.0 International License.
