This paper examines the growing role of Artificial Intelligence (AI) and Machine Learning (ML) in quantitative finance and investment decision-making. Building upon foundational theories such as Modern Portfolio Theory (MPT), the Efficient Market Hypothesis (EMH), the Capital Asset Pricing Model (CAPM), and multi-factor asset pricing models, the review explores how machine learning techniques are transforming asset return prediction, portfolio optimization, risk management, algorithmic trading, and alternative data analysis. The paper introduces an AI Investment Decision-Making Framework that organizes AI applications across five stages of the investment process: prediction, portfolio construction, risk management, trade execution, and governance. It further evaluates key challenges facing AI-driven financial systems, including overfitting, model interpretability, data quality concerns, market non-stationarity, and regulatory considerations. The review argues that artificial intelligence represents an evolutionary extension of quantitative finance rather than a replacement for its theoretical foundations. The findings suggest that the future of investment decision-making is likely to be shaped by increasingly sophisticated forms of human–AI collaboration that combine computational capabilities with human judgment, strategic reasoning, and oversight.
Kabir Maske (Sun,) studied this question.