Human-machine synergy in real estate similarity concept
More details
Hide details
1
Faculty of Geoengineering, University of Warmia and Mazury in Olsztyn, Poland
2
Institute of Geodesy and Construction, Faculty of Geoengineering, University of Warmia and Mazury in Olsztyn, Poland
Submission date: 2023-08-05
Final revision date: 2023-11-06
Acceptance date: 2023-11-22
REMV; 2024;32(2):13-30
HIGHLIGHTS
- the lack of precisely defined similar properties lead to subjective interpretation
- ceteris paribus principle creates a high risk of property value “falsification"
- the Property Cognitive Information System (PCIS) enables of synergistic data analysis
- PCIS as a human-machine based automated solution allows defining similarity
- PCIS allows for maintaining a constantly updated property comparison model.
KEYWORDS
TOPICS
ABSTRACT
The issue of similarity in the real estate market is a widely recognized aspect of analysis, yet it remains underexplored in scientific research. This study aims to address this gap by introducing the concept of a Property Cognitive Information System (PCIS), which offers an innovative approach to analyzing similarity in the real estate market. The PCIS introduces non-classical and alternative solutions, departing from the conventional data analysis practices commonly employed in the real estate market. Moreover, the study delves into the integration of artificial intelligence (AI) in the PCIS. The paper highlights the value added by the PCIS, specifically discussing the validity of using automatic ML-based solutions to objectify the results of synergistic data processing in the real estate market. Furthermore, the article establishes a set of essential assumptions and recommendations that contribute to a well-defined and interpretable notion of similarity in the context of human-machine analyses. By exploring the intricacies of similarity in the real estate market through the innovative PCIS and AI-based solutions, this research seeks to broaden the understanding and applicability of data analysis techniques in this domain.
ACKNOWLEDGEMENTS
The publication was written as a result of the authors; internship in the School of Government at the University of North Carolina, USA, co-financed by the European Union under the European Social Fund (Operational Program Knowledge Education Development), carried out in the project Development Program at the University of Warmia and Mazury in Olsztyn (POWR.03.05. 00-00-Z310/17).