Coming to Terms with Ambiguous Asset Dimensions: Quantify and Qualify Beauty, Quality and Uniqueness in the Built Environment with Machine Learning

In this project, we will first train a computer vision model from ground up. The resulting machine learning model will be the first to be fully optimised for the built environment, offering an alternative to existing transfer-learning approaches and general purpose computer vision models. Second, we will quantify and classify hard to measure or ambiguous visual building attributes such as asset uniqueness, the perceived quality of materials and designs, and the architectural beauty and character of buildings. Many of these perceptions are inherently subjective, which is why we will develop a personalised recommendation engine for residential real estate:“Based on your previous preferences, we believe you might find this building appealing...”

Project duration: May 2019 – December 2020

Internal members, ZEW – Leibniz Centre for European Economic Research, Mannheim:

• Peter Buchmann, ZEW Research Department “International Finance and Financial Management”
• Dr. Carolin Schmidt, ZEW Research Department “International Finance and Financial Management”

External members:

• Dr. Thies Lindenthal, University of Cambridge (United Kingdom)
• Wayne Xinwei Wan, University of Cambridge (United Kingdom)