Enhancing Geospatial House Price Prediction in Greater Jakarta Using XGBoost and ResNet18 Feature Fusion

Hadi Santoso; Alif Biuti Anastasya

doi:10.30595/juita.v14i1.28582

Authors

Hadi Santoso Universitas Mercu Buana
Alif Biuti Anastasya Universitas Mercu Buana

DOI:

https://doi.org/10.30595/juita.v14i1.28582

Keywords:

House price prediction, XGBoost, ResNet-18, Sentinel-2 satellite imagery, multimodal analysis

Abstract

Precise house price predictions play a vital role in shaping housing policies and informing investment decisions in urban regions such as Greater Jakarta, encompassing Jakarta, Bogor, Depok, Tangerang, and Bekasi. Most models rely exclusively on structured data, ignoring spatial and environmental factors that influence property prices. This study proposes a multimodal machine learning framework that integrates structured property data with Sentinel-2 satellite imagery within a geospatial context. The baseline dataset consists of 17 tabular variables. The ResNet-18 algorithm extracts visual environmental information from satellite imagery. The integration of both modalities through a late fusion strategy results in improved predictive performance. The baseline XGBoost achieved R² scores of 0.81 (log scale) and 0.79 (Rupiah), with an error of about 184 million Rupiah. The image-only model achieved an R² of 0.43, indicating moderate explanatory capability. Late fusion further improved performance, achieving R² values of 0.94 (log scale) and 0.93 (Rupiah), while reducing prediction error by over 40%.

Author Biographies

Hadi Santoso, Universitas Mercu Buana

Faculty of Computer Science

Alif Biuti Anastasya, Universitas Mercu Buana

Faculty of Computer Science

References

[1] R. Cellmer and K. Kobylińska, “HOUSING PRICE PREDICTION - MACHINE LEARNING AND GEOSTATISTICAL METHODS,” Real Estate Management and Valuation, vol. 33, no. 1, pp. 1–10, Mar. 2025, doi: 10.2478/remav-2025-0001.

[2] L. Chen, X. Yao, Y. Liu, Y. Zhu, W. Chen, X. Zhao and T. Chi, “Measuring impacts of urban environmental elements on housing prices based on multisource data-a case study of Shanghai, China,” ISPRS Int J Geoinf, vol. 9, no. 2, 2020, doi: 10.3390/ijgi9020106.

[3] X. Xu and Y. Zhang, “House price forecasting with neural networks,” Intelligent Systems with Applications, vol. 12, p. 52, 2021, doi: 10.1016/j.iswa.2021.20.

[4] A. Kumar, “Recommendation of Regression Models for Real Estate Price Prediction using Multi-Criteria Decision Making,” Journal of Communications Software and Systems, vol. 19, no. 3, pp. 220–229, 2023, doi: 10.24138/jcomss-2023-0102.

[5] I. Forys, “Machine learning in house price analysis: regression models versus neural networks,” in Procedia Computer Science, Elsevier B.V., 2022, pp. 435–445. doi: 10.1016/j.procs.2022.09.078.

[6] T. Quang, N. Minh, D. Hy, and M. Bo, “Housing Price Prediction via Improved Machine Learning Techniques,” in Procedia Computer Science, Elsevier B.V., 2020, pp. 433–442. doi: 10.1016/j.procs.2020.06.111.

[7] A. B. Adetunji, O. N. Akande, F. A. Ajala, O. Oyewo, Y. F. Akande, and G. Oluwadara, “House Price Prediction using Random Forest Machine Learning Technique,” in Procedia Computer Science, Elsevier B.V., 2021, pp. 806–813. doi: 10.1016/j.procs.2022.01.100.

[8] H. Sharma, H. Harsora, and B. Ogunleye, “An Optimal House Price Prediction Algorithm: XGBoost,” Analytics, vol. 3, no. 1, pp. 30–45, Mar. 2024, doi: 10.3390/analytics3010003.

[9] Z. Liu, “Real Estate Price Prediction based on Supervised Machine Learning Scenarios,” Highlights in Science, Engineering and Technology CMLAI, vol. 39, 2023.

[10] N. H. Zulkifley, S. A. Rahman, N. H. Ubaidullah, and I. Ibrahim, “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, doi: 10.5815/ijmecs.2020.06.04.

[11] J. Avanija, G. Sunitha, K. Reddy Madhavi, P. Kora, R. Hitesh, and S. Vittal E A Associate, “Prediction of House Price Using XGBoost Regression Algorithm,” Turkish Journal of Computer and Mathematics Education, vol. 12, no. 2, pp. 2151–2155, Apr. 2021.

[12] R. Tanamal, N. Minoque, T. Wiradinata, Y. Soekamto, and T. Ratih, “House Price Prediction Model Using Random Forest in Surabaya City,” TEM Journal, vol. 12, no. 1, pp. 126–132, Feb. 2023, doi: 10.18421/TEM121-17.

[13] H. Wang, Y. Hu, L. Tang, and Q. Zhuo, “Distribution of urban blue and green space in beijing and its influence factors,” Sustainability (Switzerland), vol. 12, no. 6, Mar. 2020, doi: 10.3390/su12062252.

[14] S. Chen, D. Zhuang, and H. Zhang, “GIS-Based Spatial Autocorrelation Analysis of Housing Prices Oriented towards a View of Spatiotemporal Homogeneity and Nonstationarity: A Case Study of Guangzhou, China,” Complexity, vol. 2020, 2020, doi: 10.1155/2020/1079024.

[15] C. Xue, Y. Ju, S. Li, Q. Zhou, and Q. Liu, “Research on accurate house price analysis by using gis technology and transport accessibility: A case study of xi’an, china,” Symmetry (Basel)., vol. 12, no. 8, pp. 1–21, Aug. 2020, doi: 10.3390/sym12081329.

[16] Y. Kang, F. Zhang, W. Peng, S. Gao, J. F. Duarte and C. Ratti, “Understanding house price appreciation using multi-source big geo-data and machine learning,” Land use policy, vol. 111, Dec. 2021, doi: 10.1016/j.landusepol.2020.104919.

[17] S. Jin, H. Zheng, N. Marantz, and A. Roy, “Understanding the effects of socioeconomic factors on housing price appreciation using explainable AI,” Applied Geography, vol. 169, Aug. 2024, doi: 10.1016/j.apgeog.2024.103339.

[18] M. Li and A. Stein, “Mapping land use from high resolution satellite images by exploiting the spatial arrangement of land cover objects,” Remote Sens. (Basel)., vol. 12, no. 24, pp. 1–21, Dec. 2020, doi: 10.3390/rs12244158.

[19] T. Zhang, J. Su, Z. Xu, Y. Luo, and J. Li, “Sentinel-2 satellite imagery for urban land cover classification by optimized random forest classifier,” Applied Sciences (Switzerland), vol. 11, no. 2, pp. 1–17, Jan. 2021, doi: 10.3390/app11020543.

[20] L. Liu, C. Zhang, W. Luo, S. Chen, F. Yang, and J. Liu, “New remote sensing image fusion for exploring spatiotemporal evolution of urban land use and land cover,” J. Appl. Remote Sens., vol. 16, no. 03, Aug. 2022, doi: 10.1117/1.jrs.16.034527.

[21] B. Wiatkowska, J. Słodczyk, and A. Stokowska, “Spatial-temporal land use and land cover changes in urban areas using remote sensing images and gis analysis: The case study of opole, poland,” Geosciences (Switzerland), vol. 11, no. 8, Aug. 2021, doi: 10.3390/geosciences11080312.

[22] C. Zhao, Y. Ogawa, S. Chen, T. Oki, and Y. Sekimoto, “Quantitative land price analysis via computer vision from street view images,” Eng. Appl. Artif. Intell., vol. 123, Aug. 2023, doi: 10.1016/j.engappai.2023.106294.

[23] X. Xu, “Associations Between Street-View Perceptions and Housing Prices: Subjective vs. Objective Measures Using Computer Vision and Machine Learning Techniques,” Remote Sens. (Basel)., vol. 14, no. 4, Feb. 2022, doi: 10.3390/rs14040891.

[24] L. Yang, Z. Chen, and G. Li, “Satellite Image Price Prediction Based on Machine Learning,” Remote Sens. (Basel)., vol. 17, no. 12, Jun. 2025, doi: 10.3390/rs17121960.

[25] A. Nouriani and L. Lemke, “Vision-based housing price estimation using interior, exterior & satellite images,” Intelligent Systems with Applications, vol. 14, p. 81, 2022, doi: 10.1016/j.iswa.2022.20.

[26] J. Chougale, A. Shinde, N. Deshmukh, D. Sawant, and V. Latke, “House Price Prediction using Machine learning and Image Processing,” Journal of University of Shanghai for Science and Technology, vol. 23, no. 6, Jun. 2021.

[27] Adhinata, F. D. Fitriana, G. F. Wijayanto, and A. Putra, “Corn Disease Classification Using Transfer Learning and Convolutional Neural Network,” JUITA: Jurnal Informatika, vol. 9, No. 2, Nov. 2021, doi: 10.30595/juita.v9i2.11686.

[28] F. D. Adhinata, D. P. Rakhmadani, M. Wibowo, and A. Jayadi, “A Deep Learning Using DenseNet201,” JUITA: Jurnal Informatika, vol. 9, No. 1, May 2021, doi: 10.30595/juita.v9i1.9624.

[29] A. Nur, A. Thohari, L. Triyono, I. Hestiningsih, B. Suyanto, and A. Yobioktobera, “Performance Evaluation of Pre-Trained Convolutional Neural Network Model for Skin Disease Classification,” JUITA: Jurnal Informatika, vol. 10, No. 1, May 2022, doi: 10.30595/juita.v10i1.12041.

[30] P. Y. Wang, C. T. Chen, J. W. Su, T. Y. Wang, and S. H. Huang, “Deep learning model for house price prediction using heterogeneous data analysis along with joint self-attention mechanism,” IEEE Access, vol. 9, pp. 55244–55259, 2021, doi: 10.1109/ACCESS.2021.3071306.

[31] O. Poursaeed, T. Matera, and S. Belongie, “Vision-based real estate price estimation,” Mach. Vis. Appl., vol. 29, no. 4, pp. 667–676, May 2018, doi: 10.1007/s00138-018-0922-2.

[32] G. E. Kenyon, D. Arribas-Bel, and C. Robinson, “Extracting Features from Satellite Imagery to Understand the Size and Scale of Housing Sub-Markets in Madrid,” Land (Basel)., vol. 13, no. 5, May 2024, doi: 10.3390/land13050575