Perbandingan Kinerja Logistic Regression dan Decision Tree dalam Memprediksi Produksi Padi di Sumatera
DOI:
https://doi.org/10.30812/corisindo.v1.5325Keywords:
Produksi Padi, Klasifikasi, Logistic Tegression, Decision Tree, Machine LearningAbstract
Penelitian ini membandingkan kinerja dua algoritma klasifikasi, yaitu Logistic Regression dan Decision Tree, dalam memprediksi tingkat produksi padi di delapan provinsi di Sumatera. Data yang digunakan mencakup kurun waktu 1993 hingga 2020 dan melibatkan variabel seperti curah hujan, suhu, kelembapan, dan luas panen. Seluruh data diproses melalui tahap praproses dan transformasi untuk menghasilkan model klasifikasi multi-kelas: Rendah, Sedang, dan Tinggi. Hasil evaluasi menunjukkan bahwa kedua model memiliki akurasi yang sama sebesar 79,41%. Namun, Decision Tree menunjukkan F1-score tertimbang yang sedikit lebih tinggi, yaitu 0,7815 dibandingkan dengan 0,7760 pada Logistic Regression. Hal ini mengindikasikan bahwa Decision Tree lebih efektif dalam mengenali pola data yang kompleks dan tidak seimbang. Temuan ini menunjukkan bahwa pemilihan algoritma yang sesuai sangat penting dalam mendukung keputusan strategis di sektor pertanian. Penelitian ini dapat dikembangkan lebih lanjut dengan melibatkan fitur tambahan dan algoritma prediktif lain untuk meningkatkan akurasi model.
References
[1] P. C. Saibabu, H. Sai, S. Yadav, and C. R. Srinivasan, “Synthesis of model predictive controller for an identified model of MIMO process,” Indones. J. Electr. Eng. Comput. Sci., vol. 17, no. 2, pp. 941–949, 2019, doi: 10.11591/ijeecs.
[2] M. A. Basir, M. S. Hussin, and Y. Yusof, “Integrated bio-search approaches with multi-objective algorithms for optimization and classification problem,” Telkomnika (Telecommunication Comput. Electron. Control., vol. 18, no. 5, pp. 2421–2431, 2020, doi: 10.12928/TELKOMNIKA.V18I5.15141.
[3] I. H. Rahmana, A. R. Febriyani, I. Ranggadara, Suhendra, and I. S. Karima, “Comparative study of extraction features and regression algorithms for predicting drought rates,” Telkomnika (Telecommunication Comput. Electron. Control., vol. 20, no. 3, pp. 638–646, 2022, doi: 10.12928/TELKOMNIKA.v20i3.23156.
[4] Y. A. Mohammed and E. G. Saleh, “Comparative study of logistic regression and artificial neural networks on predicting breast cancer cytology,” Indones. J. Electr. Eng. Comput. Sci., vol. 21, no. 2, pp. 1113–1120, 2020, doi: 10.11591/ijeecs.v21.i2.pp1113-1120.
[5] C. I. Imrane, N. Said, B. El Mehdi, E. K. A. Seddiq, and M. Abdelaziz, “Machine learning for decoding linear block codes: Case of multi-class logistic regression model,” Indones. J. Electr. Eng. Comput. Sci., vol. 24, no. 1, pp. 538–547, 2021, doi: 10.11591/ijeecs.v24.i1.pp538-547.
[6] H. Agusta, E. Santosa, Dulbari, D. Guntoro, and S. Zaman, “Continuous Heavy Rainfall and Wind Velocity During Flowering Affect Rice Production,” Agrivita, vol. 44, no. 2, pp. 290–302, 2022, doi: 10.17503/agrivita.v44i2.2539.
[7] Dulbari et al., “Local adaptation to extreme weather and it’s implication on sustainable rice production in Lampung, Indonesia,” Agrivita, vol. 43, no. 1, pp. 125–136, 2021, doi: 10.17503/agrivita.v43i1.2338.
[8] J. R. Asor, J. L. Lerios, S. B. Sapin, J. O. Padallan, and C. A. C. Buama, “Fire incidents visualization and pattern recognition using machine learning algorithms,” Indones. J. Electr. Eng. Comput. Sci., vol. 22, no. 3, pp. 1427–1435, 2021, doi: 10.11591/ijeecs.v22.i3.pp1427-1435.
[9] T. Amelia and R. Mohamed, “A decision tree approach based on BOCR for minimizing criteria in requirements prioritization,” Indones. J. Electr. Eng. Comput. Sci., vol. 32, no. 2, pp. 1094–1104, 2023, doi: 10.11591/ijeecs.v32.i2.pp1094-1104.
[10] H. Elmannai and A. D. Al-Garni, “Classification using semantic feature and machine learning: Land-use case application,” Telkomnika (Telecommunication Comput. Electron. Control., vol. 19, no. 4, pp. 1242–1250, 2021, doi: 10.12928/TELKOMNIKA.v19i4.18359.
[11] M. G. Hussain, B. Sultana, M. Rahman, and M. R. Hasan, “Comparison analysis of Bangla news articles classification using support vector machine and logistic regression,” Telkomnika (Telecommunication Comput. Electron. Control., vol. 21, no. 3, pp. 584–591, 2023, doi: 10.12928/TELKOMNIKA.v21i3.23416.
[12] S. B. Abhi et al., “An intelligent wind turbine with yaw mechanism using machine learning to reduce high-cost sensors quantity,” Indones. J. Electr. Eng. Comput. Sci., vol. 31, no. 1, pp. 10–21, 2023, doi: 10.11591/ijeecs.v31.i1.pp10-21.
[13] H. A. J. H. Almuhana and H. H. Abbas, “Classification of specialities in textual medical reports based on natural language processing and feature selection,” Indones. J. Electr. Eng. Comput. Sci., vol. 27, no. 1, pp. 163–170, 2022, doi: 10.11591/ijeecs.v27.i1.pp163-170.
[14] N. Agnihotri and S. K. Prasad, “Hybrid logistic regression support vector model to enhance prediction of bipolar disorder,” Indones. J. Electr. Eng. Comput. Sci., vol. 36, no. 2, pp. 1294–1300, 2024, doi: 10.11591/ijeecs.v36.i2.pp1294-1300.
[15] N. Jahan and R. Shahariar, “Predicting fertilizer treatment of maize using decision tree algorithm,” Indones. J. Electr. Eng. Comput. Sci., vol. 20, no. 3, pp. 1427–1434, 2020, doi: 10.11591/ijeecs.v20.i3.pp1427-1434.
