Expanding portfolio diversification through cluster analysis beyond traditional volatility

Investment Management and Financial Innovations, Год журнала: 2025, Номер 22(1), С. 147 - 159

Опубликована: Янв. 23, 2025

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

Язык: Английский

AI in Sustainable Investing

Advances in computational intelligence and robotics book series, Год журнала: 2025, Номер unknown, С. 383 - 416

Опубликована: Май 8, 2025

A systematic literature review (SLR) of 120 peer-reviewed articles published between 2010 and 2024, examining the role advanced technologies in sustainable investing. Using grounded theory's coding techniques, analysis identifies five key themes: I. Enhanced Data Processing Predictive Analytics, II. Algorithmic Bias Ethical Challenges, III. Market Volatility Systemic Risks, IV. Regulatory Transparency Gaps, V. Stakeholder Collaboration Trust. The chapter highlights transformative potential these improving efficiency predictive capabilities within However, it also underscores ethical, systemic, regulatory risks associated with their implementation. To address challenges, advocates for hybrid governance frameworks that combine human oversight technological precision, prioritize ethical design principles, establish agile approaches. This balanced approach aims to leverage advancements as a positive force achieving outcomes.

Язык: Английский

A Sustainable Portfolio Construction Model Based on ESG and Deep Learning Algorithms: Evidence from the U.S. Market

Computational Economics, Год журнала: 2025, Номер unknown

Опубликована: Май 10, 2025

Язык: Английский