Investigating the Impact of Building Footprints on Valuation in Automated Valuation Models

Simon Thaler, Felipe Calainho and Marc Francke

ERES from European Real Estate Society (ERES)

Abstract: This study investigates the impact of incorporating building footprint images into Automated Valuation Models (AVMs) for improved property valuation accuracy. Traditional AVMs primarily rely on property characteristics, regional data, and historical transaction records, often overlooking the geometric and spatial features represented in building footprints. This research proposes integrating Convolutional Neural Networks (CNNs) to analyze building footprint images and refine AVM predictions by modeling residuals from a baseline AVM. The dataset includes Austrian residential properties, encompassing transaction prices, property attributes, and building footprint data. By leveraging CNNs, the study aims to capture hidden patterns related to building shape, layout, and surrounding spatial distribution, enhancing the understanding of factors influencing real estate prices. Anticipated results suggest that the inclusion of spatial data in AVMs can lead to more nuanced and accurate valuations, providing valuable insights for financial institutions and the real estate industry.

Keywords: Automated Valuation Methods; Building Footprints; Convolutiona Neural Networks (search for similar items in EconPapers)
JEL-codes: R3 (search for similar items in EconPapers)
Date: 2025-01-01
New Economics Papers: this item is included in nep-big
References: Add references at CitEc
Citations:

Downloads: (external link)
https://eres.architexturez.net/doc/oai-eres-id-eres2025-194 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:arz:wpaper:eres2025_194

Access Statistics for this paper

More papers in ERES from European Real Estate Society (ERES) Contact information at EDIRC.
Bibliographic data for series maintained by Architexturez Imprints ().