Background Economic stability depends on the ability to foresee financial risk, particularly in markets that are extremely volatile. Unbalanced financial data is difficult for traditional Support Vector Machine (SVM) models to handle, which results in subpar crisis detection capabilities. In order to improve financial risk early warning models, this study combines Gaussian SVM with stochastic gradient descent (SGD) optimisation (SGD-GSVM). Methods The suggested model was developed and assessed using a dataset from China's financial market that included more than 2,000 trading days (January 2022–February 2024). Missing value management, Min-Max scaling for normalising numerical characteristics, and ADASYN oversampling for class imbalance were all part of the data pretreatment process. Key evaluation metrics, such as accuracy, recall, F1-score, G-Mean, AUC-PR, and training time, were used to train and evaluate the SGD-GSVM model to Standard GSVM, SMOTE-SVM, CS-SVM, and Random Forest. Results Standard GSVM (76% accuracy, 1,200s training time) and CS-SVM (81% accuracy, 1,300s training time) were greatly outperformed by the suggested SGD-GSVM model, which obtained the greatest accuracy of 92% with a training time of just 180 seconds. Additionally, it showed excellent recall (90%) and precision (82%), making it the most effective and efficient model for predicting financial risk. Conclusion This work offers a new method for early warning of financial risk by combining SGD optimisation with Gaussian SVM and employing adaptive oversampling for data balancing. The findings show that SGD-GSVM is the best model because it strikes a balance between high accuracy and computational economy. Financial organisations can create real-time risk management plans with the help of the suggested technique. For additional performance improvements, hybrid deep learning approaches might be investigated in future studies.

Between high-quality and high-efficiency green innovation, which can truly reduce stock price crash risk? We use data from Chinese listed companies from 2010 to 2022 to study the impact mechanism and effect of radical and incremental green innovation stock price crash risk. Results show that radical green innovation can significantly reduce stock price crash risk, and this effect is more evident than the incremental one. Radical green innovation can improve information efficiency and enhance risk management, thus reducing stock price crash risk. Besides, among companies held by trading institutions and with low analyst coverage, the inhibitory effect is more evident.

There is substantial evidence indicating that enterprises are negatively impacted by climate risk, with the most direct effects typically occurring in financial domains. This study examines A-share listed companies from 2007 to 2023, employing text analysis to develop the firm-level climate risk indicator and investigate the influence on corporate financial risk. The results show a significant positive correlation between climate risk and financial risk at the firm level. Mechanism analysis shows that the negative impact of climate risk on corporate financial condition is mainly achieved through three paths: increasing financial constraints, reducing inventory reserves, and increasing the degree of maturity mismatch. To address potential endogeneity, this study applies instrumental variable tests, propensity score matching, and a quasi-natural experiment based on the Paris Agreement. Additional tests indicate that reducing the degree of information asymmetry and improving corporate ESG performance can alleviate the negative impact of climate risk on corporate financial conditions. This relationship is more pronounced in high-carbon emission industries. In conclusion, this research deepens the understanding of the link between climate risk and corporate financial risk, providing a new micro perspective for risk management, proactive governance transformation, and the mitigation of financial challenges faced by enterprises.

We investigate the economic impact of artificial intelligence (AI) adoption in the mutual fund industry by introducing a novel measure of AI adoption based on the presence of AI skilled personnel at fund management firms. We provide robust evidence that AI adoption enhances fund performance, primarily by improving risk management, increasing attentive capacity, and enabling faster information processing. Furthermore, we find that mutual funds with higher levels of AI adoption experience greater investor net flows and exhibit lower flow-performance sensitivity. While AI adoption benefits individual funds, we find no evidence of aggregate performance improvements at the industry level.

This paper investigates whether regional negative public sentiment associated with extreme non-financial social shocks (e.g., violence or crime) will affect the resident firms’ M&A announcement return. Using a sample of 3,200 M&A deals in China, our empirical results consistently show that M&A announcement return is significantly lower after the firm’s headquarter city has experienced negative social shocks. We further find that better CSR performance helps to mitigate the impact of these negative shocks. Overall, we show that firm operations will be largely affected by the resident environment and location, and better CSR performance acts as an effective risk management strategy.

This paper develops a network to analyze inter-industry risk spillovers during high and low volatility periods. Our findings indicate that China's Industrials and Consumer Discretionary exhibit the greatest levels of spillovers in both high and low volatility states. Notably, our results demonstrate the "event-driven" character of structural changes to the network during periods of pronounced risk events. At the same time, the economic and financial network exhibits clear "small world" characteristics. Additionally, in the high volatility stage, the inter-industry risk contagion network becomes more complex, featuring greater connectivity and direct contagion paths. Furthermore, concerning the spillover connection between finance and the real sector, the real economy serves as a net exporter of risk. The study's findings can assist government agencies in preventing risk contagion between the financial market and the real economy. The empirical evidence and policy lessons provide valuable insights for effective risk management.

Developing an early warning model for company financial crises holds critical significance in robust risk management and ensuring the enduring stability of the capital market. Although the existing research has achieved rich results, the disadvantages of insufficient text information mining and poor model performance still exist. To alleviate the problem of insufficient text information mining, we collect related financial and annual report data from 820 listed companies in mainland China from 2018 to 2023 by using sophisticated web crawlers and advanced text sentiment analysis technologies and using missing value interpolation, standardization, and data balancing to build multi-source datasets of companies. Ranking the feature importance of multi-source data promotes understanding the formation of financial crises for companies. In the meantime, a novel Attention-based Fuzzy Neural Network (AFNN) was proposed to parse multi-source data to forecast financial crises among listed companies. Experimental results indicate that AFNN exhibits significantly improved performance compared to other advanced methods.

Since the global financial crisis of 2007–2009, preventing financial crises has become one of the most important objectives of regulators and banks. Although previous studies have identified the phenomenon of risk contagion in the banking system, the underlying mechanisms of risk contagion are still unclear. This study delves into the multi-stage contagion mechanism of liquidity risk based on interbank lending linkages and clearing rules and introduces a new index to quantify bank liquidity risk. We find that the contagion of liquidity risk is primarily determined by the network structure of risk exposures between banks in default and is not significantly influenced by the lending relationships of banks that remain solvent. The empirical results suggest that banks with high risk should be prioritized for cash injections to improve system liquidity. These findings offer new insights into financial risk contagion and practical recommendations for regulatory authorities formulating intervention strategies and for banks conducting risk management.

This paper addresses the dynamic tail risk in price-limited financial markets. We propose a novel censored autoregressive conditional Fr´echet model with a fiexible evolution scheme for the time-varying parameters, which allows deciphering the impact of historical information on tail risk from the viewpoint of different risk preferences. The proposed model can well accommodate many important empirical characteristics, such as thick-tailness, extreme risk clustering, and price limits. The empirical analysis of the Chinese stock market reveals the effectiveness of our model in interpreting and predicting time-varying tail behaviors in price-limited equity markets, providing a new tool for financial risk management.

Establishing a comprehensive risk management system and establishing a sound and effective internal control mechanism are important conditions for the survival and healthy development of enterprises. Enterprises should continue to innovate their internal control mechanisms, continuously improve and strengthen their internal control and risk management functions, continuously improve their internal control effectiveness, and assist in high-quality development of enterprises. The article elaborates that the digital transformation of auditing helps to achieve internal audit goals and improve the effectiveness of internal control; Blockchain technology, due to its excellent characteristics of distributed decentralization, authenticity, transparency, and tamper resistance, will help transform the methods of financial and accounting business and audit supervision; The application of blockchain technology in the field of auditing will inevitably lead to the reshaping of audit work models; Blockchain technology will become a trigger point for the audit revolution, comprehensively empowering audit and risk management work. The article introduces JD's blockchain ABS standardization solution, while Tencent and TCL Group's industrial blockchain solve the reliable transmission of trust and value at low cost, confirming that the close combination of blockchain technology with enterprise finance and auditing can assist internal control and play an important risk prevention and control role in enterprise operations. The "blockchain+audit" can achieve online real-time audit, risk assessment and warning, and data analysis becomes the core of audit content; Blockchain+auditing will become an important tool for internal control and risk management in enterprises.