This study aims to address the challenge in modern financial markets where traditional methods struggle to accurately predict and control financial information risks composed of high-dimensional, unstructured data, which is crucial for maintaining financial stability. To this end, the paper proposes a financial information risk prediction and control algorithm based on an Improved Bat Algorithm (IBA). This method enhances the global search capability of IBA to handle complex data and optimizes its local search strategy to improve prediction accuracy. Additionally, it constructs a mechanism integrating text, image, and time-series data to provide more comprehensive information support for risk models. Key findings demonstrate that extensive empirical analyses validate the algorithm's effectiveness in practical risk control: it significantly improves data processing efficiency and prediction accuracy, enables early identification of potential financial risks, and offers precise decision-making support for regulatory agencies. The empirical results also highlight the substantial enhancement of financial information integration on risk prediction models. The final conclusion indicates that this IBA-based financial information fusion risk prediction model can effectively strengthen financial market stability and provides new directions.
Wang et al. (2026) studied this question.