AI-Enhanced Fuzzy Precision in Stock Investment Decisions with Integrated Weighted Aggregation and Multivariate

This paper presents a decision support system designed for stock trading, utilizing Fuzzy IF-THEN Rules. The system utilizes three key linguistic variables as input parameters: Price-to-Earnings Ratio (PE), Earnings per Share (EPS), and Price-to-Book Ratio (PB). Its primary aim is to assist investors in making informed decisions regarding their stock investments, aiming to maximize profits in the complex and challenging stock market environment. To simplify and improve decision-making in this intricate realm, Artificial Intelligence (AI) is employed through the implementation of Fuzzy Logic (FL). The stock Investment decider is constructed by developing a Mamdani Type 2 Fuzzy Logic System using MATLAB. Previous research has highlighted the effectiveness of FL in navigating the complexities of stock trading environments. The study thoroughly assesses and validates the fuzzy rules through the application of a Fuzzy Inference System in MATLAB, ensuring a comprehensive evaluation of the proposed system's effectiveness. The model demonstrated an highest accuracy rate of 99.35% concerning real-time investment decisions and with other Machine Learning Models.