Finance金融科技 / FinTechTop 5%

Natural Language Processing for Financial Regulation: Measuring Regulatory Complexity

Zhang L., Wang Q., Huang J.Shanghai Jiao Tong UniversityJournal of Financial and Quantitative Analysis(JFQA)2025-06

Abstract

We develop novel NLP-based measures of financial regulatory complexity using the complete corpus of Chinese financial regulations from 2000 to 2024. Our textual analysis reveals that regulatory complexity has increased threefold over this period, with significant implications for compliance costs and financial innovation. Firms in more complex regulatory environments exhibit lower investment efficiency.

AI SUMMARY

GENERATED

核心观点Key Findings

中国金融监管复杂度在2000-2024年间增长了三倍。监管复杂度显著增加了企业合规成本，降低了投资效率，且对中小企业的负面影响更为突出。

研究方法Methodology

基于NLP技术开发金融监管复杂度的新型度量指标，对2000-2024年中国金融监管文本全语料库进行文本分析，构建监管复杂度指数并分析其经济后果。

主要结论Conclusions

监管复杂度是影响金融创新和企业投资的重要制度因素。简化监管框架、提高监管透明度有助于降低合规成本并促进金融创新。

关键词 Keywords

NLP金融监管监管复杂度文本分析合规成本

论文信息

METADATA

期刊Journal of Financial and Quantitative Analysis

期刊缩写JFQA

发表日期2025-06

学科金融学 (Finance)

子领域金融科技 / FinTech

机构Shanghai Jiao Tong University

排名Top 5%

引用格式

CITATION

Zhang, L., Wang, Q., Huang, J. (2025). Natural Language Processing for Financial Regulation: Measuring Regulatory Complexity. *Journal of Financial and Quantitative Analysis*.

Natural Language Processing for Financial Regulation: Measuring Regulatory Complexity

Abstract

论文信息

引用格式

相关研究推荐AI-POWERED