AI - Enabled Investment Decision Support System

ABSTRACT Retail investors increasingly rely on digital tools for investment planning; however, most available platforms either provide static advisory insights or depend heavily on expensive proprietary data and complex predictive models. This research presents the design and development of an AI-enabled, web-based investment decision support system focused on practical usability, transparency, and zero-cost deployment. The system extends traditional investment simulations by integrating advanced rule-based strategies such as Value Averaging Pro Rata and Constant Share, along with a linear regression–based forecasting module to assist users in understanding potential future trends. A secure administrative module enables structured management of equity and mutual fund datasets, version control, and automated report generation in spreadsheet format. The platform evaluates investment outcomes using financial performance metrics including Return on Investment (ROI), Compound Annual Growth Rate (CAGR), and Extended Internal Rate of Return (XIRR). Unlike research-oriented predictive studies, the emphasis of this work lies in transforming analytical outputs into actionable insights through dashboards and downloadable reports. The findings demonstrate that the integration of adaptive strategy models with forecasting and reporting features enhances decision clarity for retail investors without introducing computational or financial complexity. The proposed system highlights how AI-inspired logic, when combined with full-stack web technologies, can serve as an effective decision support mechanism in real-world financial planning scenarios. Keywords: Keywords: Investment Decision Support, Rule-Based AI, Value Averaging Pro Rata, Linear Regression Forecasting, Web-Based Financial System