ST-RAP: A Spatio-Temporal Framework for Real Estate Appraisal

Recent studies have attempted to address this limitation by adopting graph neural networks to model spatial relationships between In this paper, we introduce ST-RAP, a novel Spatio-Temporal framework properties [4, 14, 35]. These models represent spatial relationships for Real estate APpraisal. ST-RAP employs a hierarchical as a graph, with each node denoting a property. For example, in architecture with a heterogeneous graph neural network to encapsulate MugRep [35], nodes are connected based on geographical proximity, temporal dynamics and spatial relationships simultaneously.