PREDIKSI TARGET PENDAPATAN PAJAK DAERAH DI KABUPATEN SUMBAWA MENGGUNAKAN ALGORITMA EXTREME GRADIENT BOOSTING (XGBOOST)

Sukarti Sukarti; Ekastini Ekastini

doi:10.46764/teknimedia.v7i1.366

Sukarti Sukarti Universitas Teknologi Sumawa
Ekastini Ekastini Informatika Universitas Teknologi Sumbawa

DOI: https://doi.org/10.46764/teknimedia.v7i1.366

Keywords: Pajak Daerah, XGBoost, Prediksi, CRISP-DM, Machine Learning

Abstract

Locally Generated Revenue (PAD) is the primary source of funding for local governments, with local taxes being the largest component supporting revenue. In Sumbawa Regency, tax target determination is still based on historical potential and realization, resulting in suboptimal accuracy in determining tax targets. This study aims to develop a prediction model for local tax revenue targets using the XGBoost algorithm. Secondary data was obtained from the Sumbawa Regency Regional Revenue Agency (Bapenda), covering various types of local taxes for the 2021–2025 period. The research method uses the Cross Industry Standard Process for Data Mining (CRISP-DM) framework with stages of business understanding, data understanding, preprocessing, modeling, evaluation, and implementation. The evaluation results show an RMSE value of 743,314,988.84 or 743 million, MAPE of 5.34%, and R² of 0.9845, indicating low prediction errors and the model's ability to understand data patterns well. The model is then implemented into a Flask-based web system to support the data input process, model performance, and generate more accurate and data-based predictions of regional tax revenue targets, and has the potential to become a strategic tool in making decisions about determining regional tax targets.

References

[1] H. Yasser and T. D. Widajantie, “Pengaruh Pajak Daerah dan Retribusi Daerah Terhadap Pendapatan Asli Daerah Provinsi Jatim,” JIMEA | J. Ilm. MEA (Manajemen, Ekon. dan Akuntansi), vol. 6, no. 1, pp. 611–619, 2022.
[2] Mahfudh, H. Saleh, and M. Y. Saleh, Analisis Peningkatan Pendapatan Asli Daerah, vol. 1, no. 1. 2022.
[3] J. Martaviona and S. Nurhalimah, “Peran pajak daerah dalam pembangunan ekonomi lokal,” vol. 3, no. 1, pp. 265–277, 2025.
[4] M. R. Q. Rahmat Maulana, Pandri Ferdias, Agus Lukman Hakim, Zaenal Abidin, Ali Salmande, Miftah Faiz Ali Ramdhani, “Analisis Proyeksi Target Capaian Pajak Daerah Berbasis Potensi Wilayah,” J. Adm. Negara, vol. 4039, pp. 67–80, 2023, doi: 10.30656/sawala.v11i1.6554.
[5] Munaldi, Algoritma Random Forest Dan Xgboost Menggunakan Python. PT. Ganesha Kreasi Semesta, 2025.
[6] F. Puteri Marchanda Izzati, “Implementation of the XGBoost Algorithm for Predicting Monthly Regional Revenue Performance in Bandung,” J. Comput. Sci. Inf. Technol., vol. 6, no. 2, pp. 104–111, 2025.
[7] S. Hasibuan, “Analisis Clustering Pendapatan Pajak dan Retribusi Daerah di Kabupaten Sumbawa Dengan Model KDD Menggunakan Algoritma K-Means,” J. Inform. J. Pengemb. IT, no. xx, pp. 1–10, 2024.
[8] M. E. Jasman Pardede, “Prediksi Jumlah Target dan Realisasi Wajib Pajak Atas PBB – P2 Menggunakan Multi Regression, Regression Lasso, dan PCR,” J. Edukasi dan Penelit. Inform., vol. 10, no. 1, p. 1, 2024, doi: 10.26418/jp.v10i1.68890.
[9] A. P. P. Saragih, E. Irawan, and M. Safii, “Optimalisasi Metode Conjugate Gradient Polak Rebiere Untuk Memprediksi Target PBB Kecamatan Dolok Merawan,” Semin. Nas. Inform., vol. 4, no. 3, pp. 241–248, 2023, https://www.ejournal.pelitaindonesia.ac.id/ojs32/index.php/SENATIKA/article/view/3701
[10] D. R. Darmawanti, Yundari, and N. M. Huda, “Prediksi Realisasi Penerimaan Pajak Bumi Dan Bangunan Provinsi Kalimantan Barat Dengan Model Grey-Markov (1, 1),” Bul. Ilm. Math. Stat dan Ter., vol. 11, no. 3, pp. 503–512, 2022.
[11] M. Nidaa Rifdah Rahima Hambali, Memi Nor Hayati, “Peramalan Jumlah Penerimaan Bea Perolehan Hak Atas Tanah Dan Bangunan ( Bphtb ) Kota Samarinda Menggunakan Metode Single Moving Average,” J. Ris. Pembang., vol. 7, no. October 2024, pp. 78–87, 2025.
[12] A. Syahza, Metode Penelitian. Riau: UR Press Pekanbaru, 2021.