PREDICTIVE ANALYTICS-BASED DECISION SUPPORT SYSTEM FOR LAND INVESTMENT USING AI

Abstract

Land investment is considered a promising long-term financial strategy, but evaluating the true potential of land plots is often difficult due to limited analytical tools and heavy reliance on brokers. Most real estate platforms mainly focus on built properties and provide only basic information for raw land evaluation. This research proposes a predictive analytics-based decision support system that utilizes artificial intelligence to assist investors in making informed land investment decisions. The system integrates multiple datasets including historical land price trends, geographic location data, transportation accessibility, environmental indicators, and safety statistics. Machine learning algorithms such as Linear Regression, Random Forest, and K-Means Clustering are applied to analyze patterns and forecast future land value appreciation. A composite Investment Score is calculated by combining predicted growth with civic and environmental factors. Users can filter plots based on budget and visualize results through an interactive map interface. The platform also generates analytical reports summarizing investment potential and comparative insights. The modular architecture allows future expansion to multiple cities and integration with additional data sources. This approach enhances transparency and enables data-driven real estate investment decisions.