EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FactorGraph-RE: A Deep Latent Factor Learning and Graph Attention Network Framework for Intelligent Real Estate Asset Valuation

Yueyang Gao, Yuheng Huang

Fundamental Scientific Reports in Multidisciplinary Areas · 2026

DOI: 10.66238/fsrma110 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Fundamental Scientific Reports in Multidisciplinary Areas, 2026. Verfasst von Yueyang Gao und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

Gao, Y., & Huang, Y. (2026). FactorGraph-RE: A Deep Latent Factor Learning and Graph Attention Network Framework for Intelligent Real Estate Asset Valuation. Fundamental Scientific Reports in Multidisciplinary Areas. https://doi.org/10.66238/fsrma110

Vancouver

Gao Y, Huang Y. FactorGraph-RE: A Deep Latent Factor Learning and Graph Attention Network Framework for Intelligent Real Estate Asset Valuation. Fundamental Scientific Reports in Multidisciplinary Areas. 2026. doi:10.66238/fsrma110

BibTeX
@article{Gao2026,
  author = {Gao, Yueyang and Huang, Yuheng},
  title = {FactorGraph-RE: A Deep Latent Factor Learning and Graph Attention Network Framework for Intelligent Real Estate Asset Valuation},
  journal = {Fundamental Scientific Reports in Multidisciplinary Areas},
  year = {2026},
  doi = {10.66238/fsrma110}
}
Kostenlos starten →