University of Twente Student Theses


Leveraging Machine Learning and Geo-Analytics in Automatic Valuation Models to advance Real Estate Valuation

Gravier, Emil (2024) Leveraging Machine Learning and Geo-Analytics in Automatic Valuation Models to advance Real Estate Valuation.

[img] PDF
Abstract:This research project aims to improve existing approaches to property valuation. Traditional Automatic Valuation Model (AVM) methodology falls short in capturing factors accessible to human appraisers, specifically in considering the properties surrounding environment. Current AVM methodology lacks in considering environmental factors, attributed to insufficient data usage and incomplete modeling approaches. To address these limitations, we propose incorporating data sourced from a digital twin of the Cyprus real estate market, which offers a comprehensive representation of both physical and environmental aspects of properties. By leveraging this dataset, the project aims to develop a machine learning-based AVM improving upon state-of-the-art models. The focus of this research is to create a predictive model integrating machine learning techniques for property valuation. The model aims to provide a more accurate prediction of property prices, addressing limitations of existing models and enhancing decision-making for real estate stakeholders. The model's performance is evaluated against existing state-of-the-art AVM, through a target performance baseline on several metrics. Through this research, we hope to contribute to the AVM development methodology, showcasing the incorporation of environmental factors. The research outcomes may have implications for real estate stakeholders, seeking robust and precise property valuations in the real estate market.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science, 74 (human) geography, cartography, town and country planning, demography, 83 economics
Programme:Creative Technology BSc (50447)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page