FactorGraph-RE: A Deep Latent Factor Learning and Graph Attention Network Framework for Intelligent Real Estate Asset Valuation
DOI:
https://doi.org/10.66238/fsrma110Keywords:
Real Estate Valuation, Multi-Modal Learning, Graph Attention Network, Deep Learning, Asset ManagementAbstract
Accurate real estate asset valuation is fundamental to mortgage lending, real estate investment, financial risk management, and intelligent property transaction platforms, where pricing decisions are jointly influenced by property characteristics, macroeconomic conditions, regional market dynamics, and spatial interactions. However, conventional hedonic pricing models and existing deep learning methods primarily rely on manually engineered features or isolated property representations, making it difficult to capture latent financial drivers and complex spatial dependencies underlying real estate markets. To address these challenges, this paper proposes FactorGraph-RE (Deep Latent Factor Learning and Graph Attention Network Framework for Intelligent Real Estate Asset Valuation), a novel framework that integrates Deep Latent Factor Learning (DLFL) with a Graph Attention Network (GAT) for intelligent real estate asset pricing. Specifically, the proposed framework first employs a deep latent factor learning module to automatically discover hidden financial factors from heterogeneous market indicators, macroeconomic variables, and property-level attributes, thereby extending traditional multi-factor asset pricing theory to the real estate domain. A spatial-financial graph is subsequently constructed based on geographic proximity, transportation connectivity, regional economic similarity, and historical price correlation, while GAT is adopted to model neighborhood influence and regional price spillover effects. Experimental results on a large-scale real estate transaction dataset demonstrate that FactorGraph-RE outperforms state-of-the-art baseline models, reducing the Root Mean Square Error (RMSE) by 10.7% relative to the strongest graph-based baseline. These findings demonstrate that jointly modeling latent financial factors and spatial graph dependencies provides an effective and interpretable solution for intelligent real estate asset valuation.
References
[1] Rosen, Sherwin. "Hedonic prices and implicit markets: product differentiation in pure competition." Journal of political economy 82.1 (1974): 34-55.
[2] Bailey, Martin J., Richard F. Muth, and Hugh O. Nourse. "A regression method for real estate price index construction." Journal of the American Statistical Association 58.304 (1963): 933-942.
[3] Hong, Jengei, Heeyoul Choi, and Woo-sung Kim. "A house price valuation based on the random forest approach: the mass appraisal of residential property in South Korea." International Journal of Strategic Property Management 24.3 (2020): 140-152.
[4] Solovev, Kirill, and Nicolas Pröllochs. "Integrating floor plans into hedonic models for rent price appraisal." Proceedings of the web conference 2021. 2021.
[5] Peng, Hao, et al. "Lifelong property price prediction: A case study for the toronto real estate market." IEEE Transactions on Knowledge and Data Engineering 35.3 (2021): 2765-2780.
[6] Kipf, Thomas N., and Max Welling. "Semi-supervised classification with graph convolutional networks." arXiv preprint arXiv:1609.02907 (2016).
[7] Veličković, Petar, et al. "Graph attention networks." arXiv preprint arXiv:1710.10903 (2017).
[8] Li, Chih-Chia, et al. "Look around! A neighbor relation graph learning framework for real estate appraisal." arXiv preprint arXiv:2212.12190 (2022).
[9] Sijp, Willem P., and Marc K. Francke. "Graph‐Laplacian modeling of spatiotemporal effects for house price estimation." Real Estate Economics (2026).
[10] Maselli, Gabriella, and Antonio Nesticò. "Machine learning algorithms and explainable artificial intelligence for property valuation." Real Estate 2.3 (2025): 12.
[11] Fama, Eugene F., and Kenneth R. French. "A five-factor asset pricing model." Journal of financial economics 116.1 (2015): 1-22.
[12] Luo, Ruihan, Jinlin Hu, and Qingyu Sun. "Group Anomaly Detection and Risk Control of Commodity Sales Volume Data Based on LSTM-VAE Framework." Journal of Computer, Signal, and System Research 2.7 (2025): 48-57.
[13] Potrawa, Tomasz, and Anastasija Tetereva. "How much is the view from the window worth? Machine learning-driven hedonic pricing model of the real estate market." Journal of Business Research 144 (2022): 50-65.
[14] Wang, Tangtang, Kaijie Zhang, and Kuangcong Liu. "A Knowledge Graph and Deep Learning-Based Semantic Recommendation Database System for Advertisement Retrieval and Personalization." arXiv preprint arXiv:2601.00833 (2025).
[15] Su, Boyi, et al. "Study on Real Estate Investment Risk Assessment and Decision Support System Driven by Fintech." Proceedings of the 2nd International Symposium on Integrated Circuit Design and Integrated Systems. 2025.
[16] Liu, Boyang, Qingyu Sun, and LieSheng Wei. "Multimodal Forgery Recognition Algorithm and System Design for AI Frauds." Proceedings of the 2nd International Symposium on Integrated Circuit Design and Integrated Systems. 2025.
[17] Wei, Haoyan, Yuqing Wu, and Mengtong Li. "RAGN-IIoT: A Retrieval-Augmented NL2SQL Framework with Dynamic Sensor-Selection Guardrails for Industrial IoT Time-Series Data Warehouses." Journal of Computer, Signal, and System Research 2.7 (2025): 78-88.
[18] Luo, RuiHan, Nanxi Wang, and Xiaotong Zhu. "Fraud detection and risk assessment of online payment transactions on e-commerce platforms based on llm and gcn frameworks." arXiv preprint arXiv:2509.09928 (2025).
[19] Jiang, Gaozhe, et al. "Investment advisory robotics 2.0: Leveraging deep neural networks for personalized financial guidance." 2025 International Joint Conference on Neural Networks (IJCNN). IEEE, 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Yueyang Gao, Yuheng Huang
This work is licensed under a Creative Commons Attribution 4.0 International License.
License Terms (Recommended – CC BY 4.0)
All articles published in Fundamental Scientific Reports in Multidisciplinary Areas are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author(s) and source are properly cited. Users are allowed to copy, redistribute, remix, transform, and build upon the material for any purpose, including commercial use, as long as appropriate credit is given.
Authors retain copyright of their work while granting the journal the right of first publication. The journal provides immediate open access to its content on the principle that making research freely available supports a greater global exchange of knowledge.
For more information about this license, visit:
https://creativecommons.org/licenses/by/4.0/
