Financial distress poses significant risks to companies. Predicting the trajectories of firms after the onset of financial distress is as critical as predicting its occurrence. This study introduces a financial distress prognostic model (FDPM) based on random survival forests (RSFs) to forecast the development of distressed firms, addressing the persistent challenge of poor predictive performance in small-sample scenarios. Unlike traditional methods that focus on predicting the onset of financial distress, the FDPM integrates and optimizes medical prognostic models based on omics data for application in the context of financial distress prognosis, overcoming the limitations imposed by scarce data on distressed firms. Using a dataset of 281 publicly listed manufacturing firms in China marked ‘special treatment (ST)’, we find that the FDPM achieves a concordance index (c-index) of 0.844 and an area under the curve (AUC) of 0.908, and time-averaged integrated AUC of 0.876 in survival analysis, outperforming the widely used Cox regression model and several standard econometric models in financial distress prognosis. The FDPM also identified key financial indicators influencing recovery, such as the profit-to-cost ratio and the total asset growth rate. These insights enable managers to prioritize targeted interventions, providing a robust tool for navigating financial distress and improving risk management strategies.

Recent advancements in Artificial Intelligence (AI) have attracted significant attention within the managerial accounting profession. With its transformative capabilities and complexity, AI presents numerous opportunities alongside notable challenges in its adoption. This paper examines the key factors influencing AI adoption in managerial accounting and highlights common concerns faced by companies during this process. Based on interviews with representatives from 41 companies, we identified a range of factors impacting AI adoption at both institutional and individual levels. These findings offer valuable insights into AI acceptance within the field of managerial accounting.

With the swift advancement of information technology, digitalisation and intelligence have emerged as intrinsic drivers of reform and progress in enterprise risk management. Conventional approaches to financial risk early-warning predominantly rely on structured data, exhibit limited exploration of unstructured information, inadequately address the varying quality of information sources, and generally apply uniform treatment to multi-source data. In response to these shortcomings, the present study harnesses the advantages of evidence theory in managing uncertain information fusion by incorporating two-dimensional evidence theory into the financial risk early-warning framework. By integrating this with a random forest algorithm, a novel financial risk early-warning model—termed TD-DS-RF (Two-Dimensional Dempster-Shafer with Random Forest)—is established. Additionally, a financial risk early-warning lexicon is devised for publicly listed enterprises. Empirical validation utilises data from Chinese manufacturing firms listed between 2012 and 2021. The findings affirm that the TD-DS-RF model exhibits strong performance in real-world contexts, furnishing reliable decision-making support for both stakeholders and regulatory bodies, while contributing a novel conceptual lens to the domain of financial risk early-warning.

Securities analysts play a crucial role in the stock market, and their stock recommendations have an important impact on investors' investment decisions. The key to fully leveraging the value of analyst recommendations as an information resource lies in determining the reliability of these recommendations. This study proposes a method for predicting the reliability of analyst recommendations based on the Dempster-Shafer evidence theory and the LightGBM model (DS-LightGBM). The DS-LightGBM model is constructed by incorporating the LightGBM algorithm into evidence theory, which consists of three dimensions: analyst characteristics, rating characteristics, and company characteristics. In the process of reliability prediction, the initial step involves assessing the reliability of the evidence, followed by employing the D-S synthesis rule to fuse the information, along with the explainability provided by the SHAP method. The effectiveness of the proposed method is validated through experiments using analysts and A-share market data in China. When compared to the prediction outcomes of random forest, AdaBoost, and similar models, it becomes evident that the DS-LightGBM model exhibits superior prediction accuracy. Additionally, this model effectively measures the contribution and relevance of features, thereby improving the model's explainability and dependability. Consequently, it offers investors, brokers, and other information users a more precise foundation for decision-making purposes.

Security analysts play a vital role as an information intermediary in the stock market. Their stock recommendations are important references for investors. The efficiency of investment decision-making could be improved by judging the reliability of stock recommendations based on analyst characteristics and fusing the recommendations. We propose an information fusion method for security analysts’ stock recommendations based on two-dimensional Dempster-Shafer (D-S) evidence theory, which comprehensively considers the external and internal characteristics of analysts. The characteristics of analysts are used to measure the reliability of the stock recommendations and modify the evidence, then the D-S fusion rule is used for evidence fusion. Compared with the forecast results of statistical methods and machine learning methods, the two-dimensional D-S evidence theory model we proposed has a higher forecast accuracy, which effectively improves the information efficiency of the stock market and helps investors to make decisions efficiently and scientifically.

PurposeSince the implementation of the regulatory inquiry system, research on its impact on information disclosure in the capital market has been increasing. This article focuses on a specific area of study using Chinese annual report inquiry letters as the basis. From a text mining perspective, we explore whether the textual information contained in these inquiry letters can help predict financial restatement behavior of the inquired companies.Design/methodology/approachPython was used to process the data, nonparametric tests were conducted for hypothesis testing and indicator selection, and six machine learning models were employed to predict financial restatements.FindingsSome text feature indicators in the models that exhibit significant differences are useful for predicting financial restatements, particularly the proportion of formal positive words and stopwords, readability, total word count and certain textual topics. Securities regulatory authorities are increasingly focusing on the accounting and financial aspects of companies' annual reports.Research limitations/implicationsThis study explores the textual information in annual report inquiry letters, which can provide insights for other scholars into research methods and content. Besides, it can assist with decision making for participants in the capital market.Originality/valueWe use information technology to study the textual information in annual report inquiry letters and apply it to forecast financial restatements, which enriches the research in the field of regulatory inquiries.

This paper uses Chinese small and medium enterprises (SMEs) as a research sample to explore the relationship between environment, social responsibility, governance (ESG) performance and firm value creation and to test the moderating effect of government subsidies. In addition, we classify government subsidies into innovation, social responsibility, and development subsidies using a Biterm Topic Model (BTM) to explore the heterogeneous moderating effects. The results show an inverted U-shaped relationship between ESG performance and value creation in Chinese SMEs. Government subsidies have a significant moderating effect on the inverted U-shaped curve of ESG performance and value creation, and the moderating effect of different government subsidies also varies. An increase in social responsibility subsidies makes the curve inflection point shift to the left, an increase in development subsidies makes the inflection point shift to the right and the curve steeper, and innovation subsidies have no moderating effect.

The high-quality development of new energy enterprises is of great significance to promote carbon peak and carbon neutrality and cope with the global warming crisis. However, with the increasing intensity of market competition and the appropriate weakening of the expected future subsidies, how to improve their performance through the fulfillment of the social responsibility of stakeholders has become a key scientific problem to be solved. Given the features of the new energy industry, including substantial initial investment, formidable technical barriers, and a pronounced reliance on policy support, this paper takes 182 new energy concept enterprises listed in China's A-shares in 2011–2020 as the research object. Employing qualitative comparative analysis, we extract four key rules for achieving high performance in new energy enterprises from the perspective of value co-creation of core stakeholders, including capital stakeholders (shareholders and creditors), technical stakeholders (employees), policy stakeholders (government and society), and upstream and downstream stakeholders (suppliers and customers). Then, we explore the performance improvement rules of typical cases. Our findings reveal that within the realm of new energy enterprises, capital-intensive enterprises with cost leadership and tax incentives, energy-manufacturing enterprises with suppliers dependence and saving environmental input, technology-innovation enterprises with cost leadership and talents dependence, and comprehensive-mature enterprises with suppliers dependence and tax incentives are more likely to achieve high performance. The findings can better guide management practice and promote the high-quality development of new energy enterprises.

In the context of global sustainable development, the relationship between environmental, social responsibility, and governance (ESG) performance and multi-stakeholder value creation has been widely discussed. However, there is a complex causal relationship between ESG performance and value creation, many firm characteristics are involved, and there is no systematic study on them. In this study, we aim to explore the relationship between ESG performance and value creation, the joint role of firms’ internal and external characteristics in this relationship, and how the three components of ESG performance act on value creation through their various configurations. To identify complex causal relationships among variables, this study introduces rough sets method to describe these configuration relationships by generating rules. We use China’s 300 CSI-listed companies on the Shanghai and Shenzhen Stock Exchanges from 2015 to 2020 as research samples and find that firms with good ESG performance are more likely to have high-efficiency value creation; moreover, this relationship exists only among firms with specific characteristics. Additionally, different combinations of ESG components may have a differential impact on value creation, and we identify four configurations that generate high-efficiency value creation. This study contributes to guiding companies to strengthen their ESG practices and rationally allocate resources.

完善劳资共生的分配制度,是实现共同富裕的重要制度保障.借鉴两种群共生演化理论模型分析劳资共生要素,构建了劳资共生演化模型,分析劳资并生、寄生、偏利共生、互惠共生以及竞争五种不同的共生模式,并对不同的共生模式赋予管理学意义,形成完整的劳资共生发展理论.通过对2010-2020年我国上市公司劳资共生模式的分析发现,我国劳资价值分配处于非对称互惠共生模式,劳资之间的共生作用对彼此都有正的贡献,劳资双方在非互惠共生模式下都能得到有利发展;从共生作用强度看,劳方对资方正向作用更大,企业价值分配总体上对股东更加有利.

针对现有财务会计数据共享中存在开销较大、隐私安全性较低等问题,提出一种基于差分隐私的企业财务会计数据安全共享方法.通过差分隐私技术构建强化学习的形式化模型,在建模过程中引入马尔可夫决策过程,确定会计数据状态,并获得对应最优值函数,完成企业财务会计数据的动态隐私发布;在此基础上,设计会计数据协作服务,该数据协作服务由四种网络实体构成,分别为域密钥生成器、层密钥生成器、根密钥生成器和云服务器,防止企业财务会计数据存储时泄露,实现细粒度访问控制和数据写操作.通过区块链构建企业财务会计数据安全共享模型,模型由以太坊区块链、贡献者节点、访问者节点,以及链上激励模块构成,实现企业财务会计数据安全共享.通过三个实验数据集测试方法性能,测试结果表明:设计方法隐私安全性较高,能够保持较小的数据损失,且设计方法可在较低的开销下实现会计数据安全共享.

金融体系越来越多地面临气候变化带来的风险,如何避免气候风险带来的资产损失已经成为了投资者研究的重要问题.文章深入分析了气候风险对能源行业股票市场的影响机制,并在该理论的基础上,构建了基于百度搜索指数的气候风险信息数据,利用基于卷积神经网络(CNN)和长短期记忆网络(LSTM)的能源行业股票市场预测深度学习模型,选取电力设备及新能源行业、石油石化行业和煤炭行业的行业指数作为预测对象,使用2011年9月1日至2022年8月31日的气候风险关键词的百度搜索指数和行业指数历史信息数据,检验不同类型气候风险信息数据对预测能源行业指数的有效性.实证结果发现:将气候风险信息引入到行业指数预测模型中,可以有效地提高指数预测准确度;气候物理风险和气候转型风险对不同能源行业产生不同的影响,且可以提高预测的准确性.研究结论能够为市场参与者制定投资策略、风险防范和战略选择提供重要参考.

政府通过多种类型的补助支持企业可持续发展,不同类型的政府补助支持企业解决特定发展问题,如何发挥补助资源的价值提升效应是政府补助研究的重要问题.本文将政府补助按资助目的划分为创新补助、企业发展补助和社会责任补助三种类型,研究不同类型的政府补助与处于不同生命周期阶段的中小企业价值创造效率的关联关系.采用了凝聚式层次聚类与粗糙集规律挖掘模型.在分析企业价值创造影响因素的基础上,建立政府补助对企业价值创造的影响机制,运用凝聚式层次聚类解决粗糙集模型中的数据离散问题,构造政府补助、价值创造影响因素与中小企业不同发展阶段价值创造规律挖掘模型.以2009-2018年中小企业板上市公司为样本,采用国泰安数据库的数据和在该数据库基础上挖掘分类的政府补助数据.实证结果表明,高效率的企业价值创造与不同类型政府补助和影响因素之间存在非线性组态结构关系,不同类型政府补助与企业生命周期、影响价值创造因素的特征共同决定了企业高效率的价值创造.开拓了用数据挖掘方法在政府补助与企业价值创造关联关系的研究,为探索两者之间的非线性组态结构关系提供了理论基础与应用的经验.研究结论对提升政府补助的资助效率具有借鉴意义.

Recent advances in technology have accelerated digitalization and intelligence in modern business. Particularly, the increasing use of Artificial Intelligence (AI) in managerial accounting is expected to accurately measure corporate performance, provide intelligent analyses, and predict the future of a company. However, along with the benefits, ethical concerns of using AI also arise, such as deprofessionalization, data breach, and isolation among accountants. This paper explores the ethical impact of AI in managerial accounting at both pre- and post-adoption stages. Based on 47 interviews conducted with companies, an AI system vendor, and regulators, we found that data security, privacy, and misuse; accountability; accessibility; benefits and challenges; and transparency and trust of AI are among the most common ethical risks in the development and use of AI in managerial accounting. Unique ethical impacts on four types of stakeholders: developers, managers in charge of AI adoption, managerial accountants, and regulators, were also discovered.

This study constructed a financial risk early warning model based on the D-S Evidence theory-XGBoost (DS-XGBoost) and analysed the model explainability combined with SHAP. Taking China's listed manufacturing companies from 2012 to 2021 as samples, this paper combines financial indicators, corporate governance and management perception to construct a more comprehensive financial risk early warning system. It is found that the model constructed in this study improves the performance of the financial risk early warning model, quantifies the contribution and correlation of features, enhances the model's explainability and reliability, and can provide information users with a more accurate decision-making basis.

当前关于高管特征与真实盈余管理的研究大部分聚焦于高管某一特征与真实盈余管理的关联,缺乏对高管特征全面的研究;此外,当前主要是基于因果关系的推断式研究,鲜有从预测角度进行定量研究.文章以2010—2020年A股上市公司为样本,用随机森林以更加全面的视角研究高管特征对真实盈余管理的预测作用,并进一步分析对真实盈余管理预测能力影响较强的高管特征及其预测模式.研究发现:高管特征对真实盈余管理有预测作用,但其作用弱于公司自身特征;分企业性质看,民营企业高管特征比国有企业高管特征预测真实盈余管理的能力更强;在众多高管特征中,高管薪酬对真实盈余管理预测能力的影响最强,且与真实盈余管理呈现负相关关系.文章研究结论对监管真实盈余管理行为具有一定的实践意义.

考虑到传统方法在电力工程造价数据异常识别中存在识别精度低、质量差的问题,提出了一种基于卷积神经网络的电力工程造价数据异常识别方法.通过搭建密度分布函数,计算工程造价异常数据的波动系数;根据工程造价异常数据的包络特征,计算工程造价异常数据权重;利用工程造价异常数据矩阵,求解工程造价异常数据的聚类中心.实验结果表明,文中方法在识别工程造价异常数据时可以提高工程造价异常数据识别的精度和质量.