An explainable model for the mass appraisal of residences: The application of tree-based Machine Learning algorithms and interpretation of value determinants

《An explainable model for the mass appraisal of residences: The application of tree-based Machine Learning algorithms and interpretation of value determinants》

打印

作者: Muzaffer Can Iban

来源: HABITAT INTERNATIONAL,Vol.128,P.102660

语言: 英文

关键字

作者单位: Department of Geomatics Engineering, Mersin University, Çiftlikköy Campus, 33343, Mersin, Türkiye;Department of Geomatics Engineering, Mersin University, Çiftlikköy Campus, 33343, Mersin, Türkiye;Department of Civil Engineering, Sanandaj Branch, Islamic Azad University, Sanandaj, Iran;Department of Civil Engineering, Technical and Vocational University (TVU), Tehran, Iran;Department of Civil Engineering, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran;Department of Building and Real Estate, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong, China;School of Computing, Engineering and Built Environment, Edinburgh Napier University, Edinburgh, United Kingdom;Department of Architecture, School of Design and Environment, National University of Singapore, 4 Architecture Drive, Singapore;Urban and Regional Planning Department, University of Colorado Denver, CO, USA;Department of Geography & Earth Sciences, College of Liberal Arts & Sciences, The University of North Carolina at Charlotte, Charlotte, NC, USA;College of Arts and Architecture, The Pennsylvania State University, State College, Pennsylvania, USA;Department of Geography, The University of Hong Kong, Pokfulam Road, Hong Kong, China;School of Geographic and Oceanographic Sciences, Nanjing University, Nanjing, 210023, China;Key Laboratory of Coastal Zone Exploitation and Protection, Ministry of Natural Resources, Nanjing, 210023, China;Department of Urban Studies and Planning, University of Sheffield, Western Bank, Sheffield, S10 2TN, UK;Institute of Geography, Ruhr University Bochum, Universitätsstraße 150, 44801, Bochum, Germany;Jiangsu Land Development and Consolidation Technology Engineering Center, Nanjing, 210023, China;Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, 100101, China;Key Laboratory of Regional Sustainable Development Modeling, Chinese Academy of Sciences, Beijing, 100101, China;Economic School of Shandong Technology and Business University, Yantai, 264005, China;Urban Planning & Design Institute of Shenzhen, Shenzhen, 518028, China;Institute of China Studies, University of Malaya, Kuala Lumpur, 50603, Malaysia;School of Public Administration and Policy, Renmin University of China, Beijing, 100872, China

摘要: In the mass appraisal of properties, Machine Learning (ML) algorithms have produced effective and promising results. Analysts use various algorithms to train their models with limited data and make appraisals on large data sets. However, research into which value determinants the models take into account when appraising values is insufficient. This research looks at how eXplainable Artificial Intelligence (XAI) methods can be integrated with mass real estate appraisal studies. Experimental studies were carried out on a data set containing 1002 samples and 43 independent variables. Tree-based ML regressors, namely Random Forest, XGBoost, LightGBM, and Gradient Boosting, were used for training the predictive models. The performance of these regressors was compared with that of classical multiple regression analysis. The Permutation Feature Importance (PFI) technique was used for the selection of the variables that contributed the most to the training of the models. Models retrained with selected variables were locally interpreted using the SHapley Additive eXplanations (SHAP) method. In this way, it was possible to observe the value determinants that contribute to the price estimation of each real estate sample. This study demonstrates that XAI approaches should be integrated into mass real estate valuation systems specifically, and into urban and housing research more generally, helping analysts and scholars to explain their models more transparently. The outcomes of this study can be a harbinger for analysts and scholars who wish to explain their models more transparently. Last but not least, this study advocates the use of tree-based ML algorithms since they not only allow us to implement XAI approaches but also outperform the stand-alone ML regressors.