AI4BuildingESG

This project aims to provide AI solutions to the following problems in assessing environmental, social, and governance (ESG) aspects in the construction sector: the cost problem, the arbitrariness problem, the lack of data problem, and the opacity problem. As demand for ESG increases, investors will demand more accurate and timely answers to ESG issues. However, due to the lack of comparability of ESG data, metrics, and approaches, ESG rating remains a black box, which is becoming a significant bottleneck for sustainable development in the construction sector.

To solve this problem, this project will improve ESG assessment by filling in missing data and optimizing the weighting scheme. Methodologically, this project will apply advanced machine learning methods, including matrix completion and graph-based semi-supervised learning, to fill the data gap. From a machine learning perspective, predicting ESG ratings is an example of a small-data problem, where the available training data is too small to apply powerful deep learning tools. Therefore, this project will develop new algorithms for small data sets by using concepts from statistical learning theory. Finally, with the completed data and improved weighting scheme, this project will also fill the literature gap in assessing the actual impact of ESG KPIs on real estate valuation and investment performance.

This project is being carried out in close collaboration between the Chair of Real Estate Development (Prof. Bing Zhu) and the Chair of Theoretical Foundations of Artificial Intelligence (Prof. Ghoshdastidar). While Prof. Ghoshdastidar and his research team contribute their expertise in machine learning, Prof. Zhu and her research team will contribute their expertise in real estate and, in particular, ESG assessment.