Scalable Property Valuation Models via Graph-based Deep Learning

arXiv:2405.06553v1 Announce Type: new
Abstract: This paper aims to enrich the capabilities of existing deep learning-based automated valuation models through an efficient graph representation of peer dependencies, thus capturing intricate spatial relationships. In particular, we develop two novel graph neural network models that effectively identify sequences of neighboring houses with similar features, employing different message passing algorithms. The first strategy consider standard spatial graph convolutions, while the second one utilizes transformer graph convolutions. This approach confers scalability to the modeling …

abstract arxiv automated capabilities cs.ai cs.lg deep learning dependencies features graph graph-based graph neural network graph representation identify network neural network novel paper peer property relationships representation scalable spatial through type valuation via