AI-fused construction portfolio investment system with risk hedging using machine learning and long-short strategies

Abstract

Developing consistently profitable investment strategies presents a considerable challenge within the intricate and continuously evolving financial landscape. This manuscript introduces an automated investment model meticulously designed to optimize returns through dynamic portfolio management, with a focus on comprehensive short-term portfolio decision-making. Leveraging advanced methodologies, including machine learning, natural language processing (NLP), and deep learning techniques, this study develops a robust system capable of integrating various data sources, such as extensive financial indicators, technical analysis metrics, and sentiment analysis derived from NLP-based models. We delineate essential financial factors using extreme gradient boosting and are trained on historical transaction data, financial indices, and detailed technical indicators. Furthermore, the model incorporates transformer-based NLP techniques to extract sentiment and market insights from textual data. The system autonomously identifies optimal long-short portfolio combinations and trading opportunities, employing dynamic weight adjustments informed by predictive analytics and technical indicators. Simulation results demonstrate that dynamically weighted portfolios can effectively respond to diverse economic conditions, yielding stable returns and reduced volatility, regardless of market direction. Although the scope of this study is confined to the listed construction sector in Taiwan, backtesting substantiates the robustness and potential scalability of the proposed methodology. Future research may seek to explore broader market applications to further validate the generalizability of the approach; nonetheless, the current findings already indicate significant promise for practical implementation in medium-frequency trading strategies.