Analisis Komparasi Random Forest dan XGBoost untuk Prediksi Produksi Kelapa Sawit Berbasis SHAP

Risfi Ayu Sandika; Chandra Kusuma Dewa

doi:10.47065/bits.v8i2.10970

Risfi Ayu Sandika * Universitas Islam Indonesia, Yogyakarta, Indonesia
Chandra Kusuma Dewa Universitas Islam Indonesia, Yogyakarta, Indonesia

(*) Corresponding Author

DOI: https://doi.org/10.47065/bits.v8i2.10970

Keywords: Palm Oil; Production Prediction; Random Forest; XGBoost; SHAP; Multivariate Time Series

Abstract

Palm oil production is influenced by various factors, such as plant age, land area, the number of productive trees, and fertilizer usage. Production fluctuations make it difficult for companies to formulate optimal plans for production, distribution, and fertilization strategies. Unlike previous studies, this research utilizes a dataset obtained directly from the company to compare the performance of Random Forest and XGBoost algorithms in predicting palm oil production, while also analyzing which variables most significantly influence prediction results using SHAP (SHapley Additive exPlanations). The study employs historical palm oil production data from PT XYZ covering the period from January 2020 to December 2025 comprising 588 data points using a multivariate time series approach. The research stages include data preprocessing, the creation of sliding windows with sequence lengths of 3 and 6 months, model training, hyperparameter tuning, evaluation using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and the Coefficient of Determination (R²), as well as model interpretation using SHAP. The results indicate that both models achieved their best performance with a sequence length of 3 months. The XGBoost model outperformed Random Forest, achieving an MAE of 553,293, an RMSE of 1,496,990, and an R² of 0.877, whereas Random Forest recorded an MAE of 1,283,547, an RMSE of 1,792,539, and an R² of 0.824. SHAP analysis revealed that month was the most influential factor in predicting palm oil production, followed by lag_1, lag_3, and land area. This research contributes a comparison of Random Forest and XGBoost on primary palm oil production data obtained directly from the company, as well as a SHAP-based interpretation that can serve as a practical reference for PT XYZ in production planning and corporate strategy. These findings demonstrate that the combination of XGBoost and SHAP can generate accurate predictions while providing insights into the factors influencing production, thereby supporting decision-making in palm oil production management.

Downloads

Download data is not yet available.

References

M. Irpan and U. Rio, “Model Prediksi Jumlah Produksi Kelapa Sawit Menggunakan Regresi Linear Berganda Di PT.Surya Argolika Reksa,” J u r n a l I l m i a h B E T R I K : Besemah Teknologi Informasi dan Komputer, vol. 16, no. 02, hal. 122-130, Agustus 2025, doi: 10.36050/dv9sd116

Ismiasih dan H. Afroda, "Faktor Penentu Produksi Kelapa Sawit Rakyat Di Provinsi Riau," Jurnal Penelitian Pertanian Terapan, vol. 23, no. 2, hal. 211–218, 2023, doi: 10.25181/jppt.v23i2.2726.

A. P. Putra and A. M. Harahap, “Implementasi Time Series Forecasting dengan Algoritma LSTM untuk Pemantauan dan Prediksi Produktivitas Kelapa Sawit Berdasarkan Hasil Panen,” JURIKOM (Jurnal Riset Komputer), vol. 12, no. 2, pp. 46–56, Apr. 2025, doi: 10.30865/jurikom.v12i2.8495.

T. Susanti and R. Masdalipa, "Estimasi Produksi Kelapa Sawit PT. Arta Prigel Lahat Menggunakan Algoritma Deep Learning," Digital Transformation Technology (Digitech), vol. 6, no. 1, p. 73, Feb. 2026, doi: 10.47709/digitech.v6i1.7807.

W. D. U. Parwati, F. H. Nadeak, and V. Kautsar, “Analisis Pertumbuhan dan Produktivitas Kelapa Sawit pada Variasi Kerapatan Tanam,” Jurnal Agro Industri Perkebunan, vol.12, no. 2, hal. 105–116, Jul. 2023, doi: 10.25181/jaip.v12i2.3535.

D. Desrihastuti, A. Maryanti, T. E. Sabli, I. A. Mahendra, dan N. A. Hardi, "Dampak Kemiringan Lahan Terhadap Kadar Hara dan Produksi Kelapa Sawit," Jurnal Agro Industri Perkebunan, vol. 12, no. 2, hal. 59–70, 2024, doi: 10.25181/jaip.v12i2.3454.

Rossy Mirasari, P. Puspita, and R. Ramli, “Analisis Korelasi Terhadap Produksi Kelapa Sawit (Elaeis guineensis Jacq.) Dan Pemupukan NPK,” Jurnal Agrisistem, vol. 19, no. 2, pp. 102–106, Jan. 2024, doi: 10.52625/j-agr.v19i2.297.

Supijatno, F. Adrian, dan A. Junaedi, "Analisis Pengelolaan Pemupukan Tanaman Kelapa Sawit (Elaeis guineensis Jacq.) Sebagai Bagian dari Best Management Practices Di Kebun Mesuji," Buletin Agrohorti, vol. 13, no. 1, hal. 40–47, 2025, doi: 10.29244/agrob.v13i1.60817.

E. Edric and S. P. Tamba, "Prediksi Penyakit Gagal Jantung dengan Menggunakan Random Forest," Jurnal Sistem Informasi dan Ilmu Komputer Prima (JUSIKOM PRIMA), vol. 5, no. 2, pp. 176–181, Feb. 2022, doi: 10.34012/jurnalsisteminformasidanilmukomputer.v5i2.2445.

K. Aqbar and R. A. Supono, "Performance Analysis of LSTM and XGBoost Models Optimization in Forecasting Crude Palm Oil (CPO) Production at Palm Oil Mill (POM)," Int. J. Comput. Appl., vol. 185, no. 17, pp. 37–44, Jun. 2023, doi: 10.5120/ijca2023922890.

K. Khaidir, F. Fadhliani, Z. Wirda, and A. Ramadhani, "Model Prediksi Produksi Pertanian Berbasis Machine Learning dan Data Lapangan," SISFO: Jurnal Ilmiah Sistem Informasi, vol. 9, no. 2, pp. 172–182, Oct. 2025, doi: 10.29103/.v9i2.26015.

A. V. Ponce‐Bobadilla, V. Schmitt, C. S. Maier, S. Mensing, and S. Stodtmann, "Practical Guide to SHAP Analysis: Explaining Supervised Machine Learning Model Predictions in Drug Development," Clin. Transl. Sci., vol. 17, no. 11, art. no. e70056, Nov. 2024, doi: 10.1111/cts.70056.

A. Prasetyo, S. Salahuddin, and A. Amirullah, “Prediksi Produksi Kelapa Sawit Menggunakan Metode Regresi Linier Berganda,” Jurnal Infomedia, vol. 6, no. 2, p. 76, Dec. 2021, doi: 10.30811/jim.v6i2.2343.

B. Wulan Sari and D. Prabowo, “Analisis Perbandingan Prediksi Harga Rumah Dengan Random Forest, Gradient Boosting, Dan XGBoost,” Intellect : Indonesian Journal of Learning and Technological Innovation, vol. 4, no. 1, pp. 42–51, Jun. 2025, doi: 10.57255/intellect.v4i1.1385.

M. Nalenz, J. Rodemann, and T. Augustin, “Learning De-Biased Regression Trees and Forests from Complex Samples,” Mach. Learn., vol. 113, no. 6, pp. 3379–3398, Jun. 2024, doi: 10.1007/s10994-023-06439-1.

C. Lukita, L. D. Bakti, U. Rusilowati, A. Sutarman, and U. Rahardja, “Predictive and Analytics Using Data Mining and Machine Learning for Customer Churn Prediction,” Journal of Applied Data Sciences, vol. 4, no. 4, pp. 454–465, Dec. 2023, doi: 10.47738/jads.v4i4.131.

R. I. Nthangeni, C. Sigauke, T. Ravele, and T. H. Tshisikhawe, “Enhancing Short-Term Wind Energy Forecasting with XGBoost and Conformal Prediction for Robust Uncertainty Quantification,” Computation, vol. 14, no. 3, p. 56, Mar. 2026, doi: 10.3390/computation14030056.

A. Meiseles and L. Rokach, "Iterative Feature Exclusion (IFX): Mitigating Feature Starvation in Gradient Boosted Decision Trees," Knowl. Based. Syst., vol. 289, art. no. 111546, Apr. 2024, doi: 10.1016/j.knosys.2024.111546.

M. Azad, T. H. Nehal, and M. Moshkov, "A Novel Ensemble Learning Method Using Majority Based Voting of Multiple Selective Decision Trees," Computing, vol. 107, no. 1, p. 42, Jan. 2025, doi: 10.1007/s00607-024-01394-8.

U. Ahmed et al., "Hybrid Bagging and Boosting with SHAP Based Feature Selection for Enhanced Predictive Modeling in Intrusion Detection Systems," Sci. Rep., vol. 14, no. 1, p. 30532, Dec. 2024, doi: 10.1038/s41598-024-81151-1.

Bila bermanfaat silahkan share artikel ini

Berikan Komentar Anda terhadap artikel Analisis Komparasi Random Forest dan XGBoost untuk Prediksi Produksi Kelapa Sawit Berbasis SHAP