Location, location, location: Satellite image-based real-estate appraisal

Against this background, we investigated in how far the inclusion of satellite images improves the predictive accuracy of real estate pricing models and how one can explain the predictions of these models by identifying discriminative visual features between high and low price houses. For our proof-of-concept, we use real estate data from Asheville, North Carolina [1]. The Bing Maps API is used to obtain satellite images [5] with zoom level 16, depicting 600 by 600 meters around the real estate property. We trained multiple CNNs containing tabular data as well as image data as inputs and the observed house price as the output (see Figure 1). The results show that image data improves the prediction performance of house pricing models (see Table 1).