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

TL;DR

ST-RAP is a new spatio-temporal framework utilizing hierarchical graph neural networks to improve real estate appraisal accuracy by effectively modeling spatial and temporal data.

Contribution

It introduces a novel hierarchical spatio-temporal framework with heterogeneous graph neural networks for real estate valuation.

Findings

Outperforms previous methods on large-scale datasets

Effectively captures spatial and temporal dynamics

Demonstrates significant improvements in appraisal accuracy

Abstract

In this paper, we introduce ST-RAP, a novel Spatio-Temporal framework for Real estate APpraisal. ST-RAP employs a hierarchical architecture with a heterogeneous graph neural network to encapsulate temporal dynamics and spatial relationships simultaneously. Through comprehensive experiments on a large-scale real estate dataset, ST-RAP outperforms previous methods, demonstrating the significant benefits of integrating spatial and temporal aspects in real estate appraisal. Our code and dataset are available at https://github.com/dojeon-ai/STRAP.