Real estate managers must identify the value for properties in their current market. Traditionally, this involved simple data analysis with adjustments made based on manager’s experience. Given the amount of money currently involved in these decisions, and the complexity and speed at which valuation decisions must be made, machine learning technologies provide a newer alternative for property valuation that could improve upon traditional methods. This study utilizes a systematic literature review methodology to identify published studies from the past two decades where specific machine learning technologies have been applied to the property valuation task. We develop a data, reasoning, usefulness (DRU) framework that provides a set of theoretical and practice-based criteria for a multi-faceted performance assessment for each system. This assessment provides the basis for identifying the current state of research in this domain as well as theoretical and practical implications and directions for future research.
ROOT, THOMAS H.; Strader, Troy J.; and Huang, Yu-Hsiang (John)
"A Review of Machine Learning Approaches for Real Estate Valuation,"
Journal of the Midwest Association for Information Systems (JMWAIS): Vol. 2023:
2, Article 2.
Available at: https://aisel.aisnet.org/jmwais/vol2023/iss2/2