Real Estate Value Analysis Based on Spatial Consumption Patterns: A Big Data Approach for Business Intelligence

Purpose: This study investigates how big data analytics and spatial consumption patterns can transform real estate valuation. Traditional methods often fail to capture dynamic urban conditions and sudden market shocks, as seen during the COVID-19 crisis. By integrating business intelligence, geographic information systems, and AI, this research aims to enhance valuation accuracy and market transparency. Research design, data and methodology: A systematic literature review was conducted following PRISMA 2020 guidelines. Peer-reviewed journal articles from 2020–2025 were selected through databases such as Scopus, Web of Science, and Google Scholar. Studies focusing on spatial data analytics, property valuation, and business intelligence systems were included, while conference papers, book chapters, and non-English sources were excluded. Results: The review identified four major value dimensions emerging from spatial data analytics: location intelligence, market prediction, consumer behavior insights, and risk assessment. These dimensions collectively highlight how spatial consumption patterns provide actionable intelligence for investors, developers, and policymakers. Empirical evidence demonstrates improvements. Conclusions: Evidence-based tools for real estate valuation. By integrating machine learning, GIS, and business intelligence, stakeholders can achieve competitive advantage through enhanced decision-making. The study emphasizes the need to bridge methodological debates and advance real-world applications of technology-enabled property assessment models.