CIPHER: Interpretable Price Inference by Fusing Mobility Networks and ZIP-Level Socioeconomics

Shenghuan Wang

doi:10.54097/xzwbga12

Authors

Shenghuan Wang

DOI:

https://doi.org/10.54097/xzwbga12

Keywords:

Heterogeneous Graph Transformer (HGT), Typed Mobility Graphs, Housing Price Inference, ZIP-Level Socioeconomics, Explainable Graph Learning.

Abstract

Urban housing prices arise out of the nuanced interplay of neighbourhood socioeconomic, land-use, and mobility. This paper presents the Construction–Integration–Prediction–Hypothesis–Explanation–Reproducibility (CIPHER) framework—an interpretable cross-city model combining different types of mobility graphs (parking, metro, and bike) and ZIP-level features within ZIP Code Tabulation Areas (ZCTAs) including parks, income, education, and schools, through a Heterogeneous Graph Transformer (HGT). Here, CIPHER denotes: Construction of a type-aware urban graph; Integration of ZIP context at the node level for early fusion; Prediction with a type-specific multi-task head centered on median price; Hypothesis-driven probes separating structure from parameters via hard edge deletions and value-only scaling; Explanation via Input×Gradient (IXG) and Integrated Gradients (IG) attributions aggregated from nodes to ZCTAs; and Reproducibility through schemas and manifests across cities. Comparisons of San Francisco (SF) and New York City (NY) show CIPHER achieving price prediction accuracy with between 0.77 and 0.81, with stronger performance for metro in NY and for parking in SF. The ancillary population task has poor fit. Discussion of edge removal points out neighbourhood structure dependence, and value-only scaling captures parameter robustness. Attributions at the ZIP-level provide policy-relevant maps distinguishing between corridor-driven and community-driven areas.

Downloads

Download data is not yet available.

References

[1] G. Jin, Y. Liang, Y. Fang, Z. Shao, J. Huang, J. Zhang, Y. Zheng, Spatio-temporal graph neural networks for predictive learning in urban computing: A survey. arXiv: 2303.14483 (2023). https://doi.org/10.48550/arXiv.2303.14483.

[2] Z. Li, B. Chen, S. Wu, M. Su, J. Chen, B. Xu, Deep learning for urban land use category classification: A review and experimental assessment. Remote Sens. Environ. 311, 114290 (2024). https://doi.org/10.1016/j.rse.2024.114290.

[3] M. Z. U. Rehman, S. M. S. Islam, D. Blake, A. Ulhaq, N. Janjua, Deep learning for land use classification: A systematic review of hyperspectral–LiDAR data fusion. Artif. Intell. Rev. 58, 272 (2025). https://doi.org/10.1007/s10462-025-11265-z.

[4] S. S. S. Das, M. E. Ali, Y.-F. Li, Y.-B. Kang, T. Sellis, Boosting house price predictions using geo-spatial network embedding. Data Min. Knowl. Discov. 35, 2221–2250 (2021). https://doi.org/10.1007/s10618-021-00789-x.

[5] Z. Wang, H. Li, and R. Rajagopal, Urban2Vec: Incorporating street-view imagery and POIs for multi-modal urban neighborhood embedding, in Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI-20), New York, NY, USA, February 7–12 (2020), 1013–1020. https://doi.org/10.1609/aaai.v34i01.5450.

[6] S. Dhanasekaran, D. Gopal, J. Logeshwaran, N. Ramya, A. O. Salau, Multi-model traffic forecasting in smart cities using graph neural networks and transformer-based multi-source visual fusion for intelligent transportation management. Int. J. Intell. Transp. Syst. Res. 22, 518–541 (2024). https://doi.org/10.1007/s13177-024-00413-4.

[7] P. Liu, Y. Wang, S. De Sabbata, B. Lei, F. Biljecki, J. Tang, R. Stouffs, Living upon networks: A heterogeneous graph neural embedding integrating waterway and street systems for urban form understanding. Environ. Plan. B Urban Anal. City Sci. 0(0) (2025). https://doi.org/10.1177/23998083251358527.

[8] W. Zhang, H. Liu, L. Zha, H. Zhu, J. Liu, D. Dou, H. Xiong, MugRep: A multi-task hierarchical graph representation learning framework for real estate appraisal, in Proceedings of the 27th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Singapore, August 14–18 (2021), 3937–3947. https://doi.org/10.1145/3447548.3467187.

[9] F. Moghimi, R. A. Johnson, A. Krause, Rethinking real estate pricing with transformer graph neural networks (T-GNN), in Proceedings of 2023 IEEE International Conference on Machine Learning and Applications, Jacksonville, FL, USA, December 15–17 (2023), 1405–1411. https://doi.org/10.1109/ICMLA58977.2023.00212.

[10] P. Brimos, A. Karamanou, E. Kalampokis, M. E. Mamalis, K. Tarabanis, Explainable graph neural networks on linked statistical data for predicting Scottish house prices, in Proceedings of the 27th Pan-Hellenic Conference on Informatics, Lamia, Greece, November 24–26 (2023), 36–41. https://doi.org/10.1145/3635059.3635065.

[11] A. Karamanou, P. Brimos, E. Kalampokis, K. Tarabanis, Explainable graph neural networks: An application to open statistics knowledge graphs for estimating house prices. Technologies. 12, 128 (2024). https://doi.org/10.3390/technologies12080128.

[12] M. Geerts, S. vanden Broucke, J. De Weerdt, Graph neural networks for house price prediction: Do or don’t? Int. J. Data Sci. Anal. 20, 3563–3593 (2025). https://doi.org/10.1007/s41060-024-00682-y.

[13] C. Chen, J. Wang, D. Li, X. Sun, J. Zhang, C. Yang, B. Zhang, Unraveling nonlinear effects of environment features on green view index using multiple data sources and explainable machine learning. Sci. Rep. 14, 30189 (2024). https://doi.org/10.1038/s41598-024-81451-6.

[14] Y. Xie, J. Zhang, Y. Li, Z. Zhu, J. Deng, Z. Li, Integrating multi-source urban data with interpretable machine learning for uncovering the multidimensional drivers of urban vitality. Land. 13, 2028 (2024). https://doi.org/10.3390/land13122028.

[15] W. Liu, Z. Yang, C. Gui, G. Li, H. Xu, Investigating the nonlinear relationship between the built environment and urban vitality based on multi-source data and interpretable machine learning. Buildings. 15, 1414 (2025). https://doi.org/10.3390/buildings15091414.

[16] M. N. Tygesen, F. C. Pereira, F. Rodrigues, Unboxing the graph: Towards interpretable graph neural networks for transport prediction through neural relational inference. Transp. Res. Part C Emerg. Technol. 146, 103946 (2023). https://doi.org/10.1016/j.trc.2022.103946.