In modern land management science, Automated Valuation Models (AVMs) are gradually replacing manual surveys due to their ability to process massive volumes of data. Integrating data from real estate transactions, transport infrastructure, demographic dynamics, and environmental indicators into advanced Hedonic Price Models significantly improves valuation accuracy. Machine learning algorithms such as XGBoost and Random Forest enable land value prediction with substantially lower error rates compared to traditional comparison-based methods. This technology facilitates transparency in land financial markets, enabling governments to regulate markets more effectively and curb speculation. The development of a national land price database serves as a strategic foundation for ensuring stability, balancing stakeholder interests, and enhancing public budget management through evidence-based land taxation policies (Wang & Li, 2019).
Furthermore, the application of big data in land valuation is not limited to transactional purposes but also supports strategic planning. When land price variables are analyzed in relation to socio-economic indicators, authorities can identify potential areas for infrastructure development and forecast urbanization trends. This contributes to fairer land acquisition and compensation policies, thereby reducing complex disputes and complaints. The implementation of AVM systems requires data harmonization across governmental agencies, ultimately improving the quality of national cadastral governance. This represents an inevitable advancement in digital land administration, where data becomes a core resource for guiding sustainable development, ensuring transparency, and fostering a favorable investment environment for both public and private sectors in the long term.
Authors: Hao Phu Dong, Binh Thanh Nguyen*
References:
Wang, D., & Li, V. J. (2019). Mass appraisal models of real estate in the 21st century: A systematic literature review. Sustainability, 11(24), 7006.