Real Estate Valuation in the Age of Artificial Intelligence - Modern Machine Learning Algorithms and their Application in Property Appraisal

Aug 4, 2026

Upload by Patrick

This dissertation investigates how modern machine learning can automate and improve real estate valuation, shifting from human-driven appraisal to data-driven predictive methods. It formulates research questions, motivates the need for more consistent valuation approaches, and documents the contributions of co-authored submissions and academic dissemination. Using structured datasets and clearly defined modeling components, it presents expert functions, baseline and advanced algorithms such as OLS, GAM, and XGBoost, and a testing framework. Evaluation focuses on suitable performance metrics and practical implications for property appraisal workflows.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages128

Reading Time5 h 23 min

AccessFree to download

Introduction

Motivation and Background

Research Questions

Co-Authors, Submissions and Conference Presentations

References

From Human Business to Machine Learning – Methods for Automating Real Estate Appraisals and their Practical Implications

Abstract

Introduction

Literature Review

Data

Methodology

Results

Real Estate Valuation in the Age of Artificial Intelligence – Modern Machine Learning Algorithms and their Application in Property Appraisal A dissertation presented for the degree of“Doktor der Wirtschaftswissenschaften” [Dr. rer. pol.] Submitted to the Faculty of Business, Economics, and Management Information Systems at the University of Regensburg by MORITZ STANG M.Sc. Real Estate Economics (University of Regensburg) Supervisors: Prof. Dr. Wolfgang Schäfers Prof. Dr. Tobias Just Dissertation zur Erlangung des Grades eines Doktors der Wirtschaftswissenschaft Eingereicht an der Fakultät für Wirtschaftswissenschaften der Universität Regensburg Vorgelegt von: Moritz Stang M.Sc. Immobilienwirtschaft (Universität Regensburg) Tag der Disputation: 20. Juli 2023 Berichterstatter: Prof. Dr. Wolfgang Schäfers Prof. Dr. Tobias Just Real Estate Valuation in the Age of Artificial Intelligence – Modern Machine Learning Algorithms and their Application in Property Appraisal Moritz Stang Acknowledgments Without the support of various people, this dissertation in its current form would not have been possible. Therefore, I would like to take the opportunity to express my gratitude to these individuals. First and foremost, I would like to express my appreciation to my supervisor, Prof. Dr. Wolfgang Schäfers. I thank him for his unwavering support, the inspiring discussions and the ongoing opportunities for growth and development during the last years. The collaboration with him has been immensely beneficial both academically and personally for me. Additionally, I would like to thank Prof. Dr. Tobias Just for his support, valuable comments, and taking over as secondary supervisor. Next, I would like to thank my co-authors Bastian Krämer, Dr. Cathrine Nagl, Prof. Dr. Wolfgang Schäfers, and PD Dr. Marcelo Cajias. Without them, completing and publishing the individual papers would not have been possible. In particular, I would like to express my sincere gratitude to Bastian Krämer for his valuable contribution to the completion of this dissertation. His scientific and personal intellect has greatly assisted me throughout this journey. I will always cherish the hours-long working sessions and extensive discussions we had together. A special thanks also goes to my colleagues at the IRE| BS Institute, especially Bastian Krämer, Daniel Promper, Benedict von Ahlefeldt-Dehn, Nino Paulus, Jürgen Deppner, and Dr. Cathrine Nagl. Each and every one of you has shown me over the past three years what it means to work in an ambitious team. Not only professionally, but also personally, you have helped me greatly, for which I am very grateful. From the bottom of my heart, I also want to thank my family and friends for their support. Specifically, I would like to thank my father Dr. Joachim Stang, my mother Birgit Schabesberger-Stang, and my sister Marlene Stang. Not only during the period of my dissertation, but also since my birth, I can always count on your support. I am grateful foryour relentless guidance, which has played an integral role in shaping me into the person Iam today. Thank you for always being there for me. Last but not least, I would like to express my heartfelt gratitude to the partner by my side, Verena Lehner. Dear Verena, words cannot express how grateful I am for all your support and love. Without you, the past years would have been only half as fulfilling and worthwhile. I look forward to a joint future with you! The world belongs to both of us and the rest of our family! Table of Contents List of Tables ............................................................................................................... VIII List of Figures ................................................................................................................ IX 1 Introduction ............................................................................................................

FAQs

What is the central focus of the dissertation?

The dissertation focuses on automating and improving real estate valuation using modern machine learning methods, highlighting practical implications for property appraisal.

Which machine learning models are discussed?

It discusses expert function and multiple modeling approaches including Ordinary Least Square Regression (OLS), Generalized Additive Model (GAM), and Extreme Gradient Boosting (XGBoost), along with testing and evaluation.

How does the dissertation evaluate the proposed approaches?

It describes a testing concept and evaluation metrics, using the model results to assess performance relevant to property appraisal.

Aug 4, 2026

Upload by Patrick