Article Sidebar

Download
PDF

Main Article Content

Abstract

Penetapan harga rumah di kawasan Jabodetabek masih bergantung pada penilaian manual yang subjektif sehingga menimbulkan ketimpangan informasi antara penjual dan pembeli. Penelitian ini membandingkan empat algoritma pembelajaran mesin, yaitu regresi linear, hutan acak, peningkatan gradien berbasis histogram, dan ansambel bertumpuk, untuk memprediksi harga rumah berdasarkan 3.508 data listing dari sembilan kota dan kabupaten. Kontribusi utama penelitian adalah perancangan fitur dari perspektif pengembang properti, meliputi rasio koefisien dasar bangunan, kepastian legal sertifikat, tingkat daya listrik, skor fasilitas premium, dan indikator kawasan bermerek, yang dipadukan dengan fitur geospasial berupa jarak ke pusat ekonomi. Dua skenario fitur diuji untuk mengukur kontribusi fitur tersebut. Model peningkatan gradien menghasilkan kinerja terbaik dengan koefisien determinasi sebesar 0,929 dan galat persentase absolut rata-rata sebesar 18,84 persen. Penambahan fitur geospasial dan perspektif pengembang terbukti meningkatkan akurasi prediksi secara konsisten dan signifikan.

Keywords

Geospasial Machine Learning Supervised Learning Data Science

Article Details

License

Copyright (c) 2026 Muhammad Alif Ramadhan Ramadhan, Maria Bestarina Laili Laili, Shafa Aura Ayu Ramadhan

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

References

  1. W. K. O. Ho, B. S. Tang, and S. W. Wong, "Predicting property prices with machine learning algorithms," Journal of Property Research, vol. 38, no. 1, pp. 48–70, 2021.
  2. R. A. Mora-García, M. F. Céspedes-López, and V. R. Pérez-Sánchez, "Housing price prediction using machine learning algorithms in COVID-19 times," Land, vol. 11, no. 11, 2022.
  3. A. Soltani, M. Heydari, F. Aghaei, and C. J. Pettit, "Housing price prediction incorporating spatio-temporal dependency into machine learning algorithms," Cities, vol. 131, 2022.
  4. L. Breiman, "Random forests," Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
  5. J. H. Friedman, "Greedy function approximation: a gradient boosting machine," The Annals of Statistics, vol. 29, no. 5, pp. 1189–1232, 2001.
  6. T. Chen and C. Guestrin, "XGBoost: a scalable tree boosting system," in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016, pp. 785–794.
  7. S. M. Lundberg and S. I. Lee, "A unified approach to interpreting model predictions," in Advances in Neural Information Processing Systems, vol. 30, 2017, pp. 4765–4774.
  8. M. C. Iban, "An explainable model for the mass appraisal of residences: the application of tree-based machine learning algorithms and interpretation of value determinants," Habitat International, vol. 128, 2022.
  9. H. Santoso et al., "Enhancing geospatial house price prediction in Greater Jakarta using XGBoost and ResNet18 feature fusion," JUITA: Jurnal Informatika, 2026.
  10. A. M. Saputro et al., "Predicting property prices using MLR, gradient boosting, and random forest: a case study in South Tangerang, Indonesia," in Proc. 8th Int. Conf. New Media Studies (CONMEDIA), 2025.
  11. T. Wiradinata et al., "Post-pandemic analysis of house price prediction in Surabaya: a machine learning approach," Journal of Southwest Jiaotong University, vol. 57, no. 5, 2022.
  12. N. H. Zulkifley et al., "House price prediction using a machine learning model: a survey of literature," International Journal of Modern Education and Computer Science, vol. 12, no. 6, pp. 46–54, 2020.
  13. F. Pedregosa et al., "Scikit-learn: machine learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
  14. D. H. Wolpert, "Stacked generalization," Neural Networks, vol. 5, no. 2, pp. 241–259, 1992.
  15. N. Barizki, "Daftar harga rumah Jabodetabek," Kaggle, 2022. [Online]. Available: https://www.kaggle.com/datasets/nafisbarizki/daftar-harga-rumah-jabodetabek. [Accessed: Jun. 11, 2026].