OPTIMIZING SHARE MARKET PORTFOLIOS: A COMPARATIVE STUDY OF TRADITIONAL AND AI-DRIVEN INVESTMENT STRATEGIES

Abstract

The increasing complexity and volatility of global financial markets have intensified the need for advanced approaches to portfolio optimization. Traditional investment strategies, grounded in fundamental analysis, technical analysis, and rule-based portfolio theories such as Modern Portfolio Theory (MPT), have historically served as the foundation for decision-making in equity markets. However, recent advancements in artificial intelligence (AI), including machine learning, deep learning, and automated trading algorithms, have introduced data-driven alternatives capable of processing large-scale market information and improving predictive accuracy. This study provides a comparative evaluation of traditional and AI-driven investment approaches by assessing performance indicators such as returns, risk exposure, Sharpe ratio, decision-making speed, and adaptability to market fluctuations. The analysis utilizes historical market datasets and simulation-based modelling to evaluate the efficiency and scalability of each strategy. Findings indicate that AI-driven models outperform traditional methods in dynamic and high-frequency trading environments due to superior pattern recognition and real-time processing capabilities, while traditional strategies remain advantageous for long-term stability and interpretability. The study concludes that a hybrid framework leveraging both human expertise and AI-driven analytics may offer the most robust pathway for optimizing share market portfolios. The results provide strategic insights for investors, financial institutions, and policymakers exploring modern investment ecosystems in the era of digital finance.