The study reviews the application of machine learning tools in financial investment portfolio management, focusing on cluster analysis for asset allocation, diversification, and risk optimization. The paper aims to explore the use of clustering analysis to broaden the concept of portfolio diversification beyond traditional volatility metrics. An open dataset from Yahoo Finance includes a ten-year historical period (2014–2024) of 130 actively traded securities from international stock markets used. Dataset selection prioritizes top liquidity and trading activity. Python analytical tools were employed to clean, process, and analyze the data. The methodology combines classical Markowitz optimization with clustering analysis techniques, highlighting variance-return trade-offs. Various asset characteristics, including annualized return, standard deviation, Sharpe ratio, correlation with indices, skewness, and kurtosis, were incorporated into the clustering models to reveal hidden patterns and groupings among financial assets. Results show that while clustering enhances insights into asset diversity, classical approaches remain historically superior in optimizing risk-adjusted returns. This study concludes that clustering complements, rather than replaces, classical methods by broadening the understanding of diversification and addressing many diversity factors, such as metrics of the technical, graphical, and fundamental analysis. The paper also introduces the diversity rate based on clustering, which measures the variance balance by all features within and between clusters, providing a broader perspective on diversification beyond traditional metrics. Future research should investigate dynamic clustering techniques, integrate fundamental economic indicators, and develop adaptive models for effective portfolio management in evolving financial markets.