Extracting real estate values of rental apartment floor plans using graph convolutional networks
This work addresses the problem of automated real estate valuation for rental apartments, offering a domain-specific incremental improvement by integrating GCNs with existing methods.
The researchers tackled the problem of estimating real estate values from rental apartment floor plans by using graph convolutional networks (GCNs) on access graphs extracted from images, resulting in significantly improved rent estimation accuracy compared to conventional models and enabling analysis of spatial configuration rules that influence floor plan value.
Access graphs that indicate adjacency relationships from the perspective of flow lines of rooms are extracted automatically from a large number of floor plan images of a family-oriented rental apartment complex in Osaka Prefecture, Japan, based on a recently proposed access graph extraction method with slight modifications. We define and implement a graph convolutional network (GCN) for access graphs and propose a model to estimate the real estate value of access graphs as the floor plan value. The model, which includes the floor plan value and hedonic method using other general explanatory variables, is used to estimate rents and their estimation accuracies are compared. In addition, the features of the floor plan that explain the rent are analyzed from the learned convolution network. Therefore, a new model for comprehensively estimating the value of real estate floor plans is proposed and validated. The results show that the proposed method significantly improves the accuracy of rent estimation compared to that of conventional models, and it is possible to understand the specific spatial configuration rules that influence the value of a floor plan by analyzing the learned GCN.