<![CDATA[In the era of digital transformation and data-driven decision-making, property companies are increasingly challenged by the complexity of managing vast, diverse, and unstructured data. Knowledge Discovery Systems (KDS) have emerged as vital tools for extracting valuable insights to support strategic functions such as property valuation, market analysis, and urban planning. This paper aims to investigate the trends and challenges in implementing KDS in property companies through a Systematic Literature Review (SLR) using the PRISMA framework. A total of 23 relevant publications from 2020 to 2025 were reviewed. The study finds that KDS applications span from real estate price prediction using machine learning to knowledge representation using semantic models. However, the implementation of KDS still faces significant barriers such as limited interdisciplinary collaboration, poor data quality, domain-specific constraints, and resistance to technological adoption. The results of this review contribute to a better understanding of how KDS can be effectively utilized in the property sector. It also highlights the need for future research to improve system adaptability, model explainability, and integration with domain knowledge to foster more intelligent, data-driven organizations]]>
Copyrights © 2026
