摘要
以2010-2022年中国A股上市2702家制造企业为样本,运用Word2Vec神经网络模型构建文本词典获取数据资产信息披露指标,探究数据资产信息披露与制造企业债务融资成本的关系。研究发现,数据资产信息披露程度越高,制造企业债务融资成本越低;进一步研究发现,数据资产信息披露能通过提高分析师盈余预测准确率和降低债务违约风险两条路径降低制造企业债务融资成本,并且数据资产信息披露在非国有制造企业和治理水平较高的制造企业中促进作用更加显著。因此,应持续完善上市公司数据资产信息披露准则,缓解企业与债权人之间的信息不对称,进而优化企业的金融资源配置能力。
Taking 2702 manufacturing companies listed on China’s A-share market from 2010 to 2022 as a sample,the Word2Vec neural network model was used to build a text dictionary to obtain data asset information disclosure indicators,and explore the relationship between data asset information disclosure and debt financing costs of manufacturing companies.The study found that the higher the degree of data asset information disclosure,the lower the debt financing costs of manufacturing companies;further research found that data asset information disclosure reduces the debt financing costs of manufacturing companies through two paths:improving the accuracy of analysts’earnings forecasts and reducing debt default risks.Moreover,the promotion effect of data asset information disclosure is more significant in non-state-owned manufacturing companies and manufacturing companies with higher governance levels.Therefore,the information disclosure standards for data assets of listed companies should continue to be improved to alleviate the information asymmetry between companies and creditors,thereby optimizing the company’s financial resource allocation capabilities.
作者
王文彦
张红梅
张目
Wang Wenyan;Zhang Hongmei;Zhang Mu
出处
《金融理论与实践》
北大核心
2024年第2期38-50,共13页
Financial Theory and Practice
基金
国家自然科学基金项目“基于文本信息的科技型中小企业信用风险识别机理研究”(71861003)
贵州财经大学校级重点培育学科、急需学科方向专项项目“大数据企业的信用风险预测及评价研究”(2020ZJXK20)的阶段性成果。
