The increasing complexity of financial markets and the growing need for personalisation present significant challenges to the traditional investment advisory model. To address this issue, this paper puts forth a proposal for an investment advisor robot 2.0 system based on deep neural networks. This system is designed to offer bespoke investment recommendations aligned with the risk appetite, financial objectives, and market dynamics of individual investors. The proposed method employs a long short-term memory network (LSTM) to generate personalised investment strategies in real time through the analysis of historical market data, investor behaviour data and real-time financial information. The innovation lies in the introduction of a multi-objective optimisation mechanism, which automatically adjusts the allocation of the portfolio through deep learning algorithms, optimises the balance between risk and return, and significantly improves the accuracy and practicality of investment recommendations. The experimental results demonstrate that, in comparison to the conventional investment advisory model, the system exhibits enhanced resilience in responding to market volatility across a range of simulated scenarios. It is also evident that the system is capable of formulating more forward-thinking investment strategies, while simultaneously demonstrating heightened stability and yield.

Dynamic hedging strategies are essential for effective risk management in derivatives markets, where volatility and market sentiment can greatly impact performance. This paper introduces a novel framework that leverages large language models (LLMs) for sentiment analysis and news analytics to inform hedging decisions. By analyzing textual data from diverse sources like news articles, social media, and financial reports, our approach captures critical sentiment indicators that reflect current market conditions. The framework allows for real-time adjustments to hedging strategies, adapting positions based on continuous sentiment signals. Backtesting results on historical derivatives data reveal that our dynamic hedging strategies achieve superior risk-adjusted returns compared to conventional static approaches. The incorporation of LLM-driven sentiment analysis into hedging practices presents a significant advancement in decision-making processes within derivatives trading. This research showcases how sentiment-informed dynamic hedging can enhance portfolio management and effectively mitigate associated risks.

This study employs LightGBM, a gradient boosting decision tree model, to predict stock returns and identify key pricing factors in the Chinese A-share market. The empirical analysis yields two main findings. First, LightGBM demonstrates superior predictive performance, achieving a monthly out-of-sample R² of 2.13%, more than doubling the 0.95% of traditional OLS regression. This advantage translates into significant economic gains: a LightGBM-based long-short strategy generates a monthly return of 2.63% with a Sharpe ratio of 1.77, substantially outperforming both the OLS-based strategy and the market benchmark. Second, through feature importance analysis, this study finds that liquidity and volatility-related characteristics are the most influential predictors of stock returns in China, consistent with recent literature suggesting the predominant role of market microstructure factors in emerging markets. These findings highlight the potential of machine learning techniques in asset pricing and provide new insights into return prediction in the Chinese stock market.

Large language models (LLMs) have emerged as powerful tools in the field of finance, particularly for risk management across different asset classes. In this work, we introduce a Cross-Asset Risk Management framework that utilizes LLMs to facilitate real-time monitoring of equity, fixed income, and currency markets. This innovative approach enables dynamic risk assessment by aggregating diverse data sources, ultimately enhancing decision-making processes. Our model effectively synthesizes and analyzes market signals to identify potential risks and opportunities while providing a holistic view of asset classes. By employing advanced analytics, we leverage LLMs to interpret financial texts, news articles, and market reports, ensuring that risks are contextualized within broader market narratives. Extensive backtesting and real-time simulations validate the framework, showing increased accuracy in predicting market shifts compared to conventional methods. The focus on real-time data integration enhances responsiveness, allowing financial institutions to manage risks adeptly under varying market conditions and promoting financial stability through the advanced application of LLMs in risk analysis.