PurposeThe paper focuses on the variables that help analyze peer-to-peer (P2P) lending platforms. It explores the characteristic factors of identifying problematic platforms, and designs a P2P platform risk early warning model.Design/methodology/approachWith the help of web crawler software, this paper crawls the information of 1427 P2P platforms from the two largest third-party lending information platforms (i.e. P2Peye and WDZJ) in China. SPSS 22.0 was mainly used for basic descriptive statistical analysis, reliability and validity analysis, and regression analysis of the data. MPLUS 7.0 was used for confirmatory factor analysis and structural equation models analysis.FindingsBased on the multi-dimensional information, this paper performs text mining to develop an investor sentiment index. This study shows that the characteristics of the platform (i.e. basic features, capital security, operations management, and social network) have a significant impact on identifying problematic platforms.Research limitations/implicationsThere are some limitations to this research. In the process of model construction, some external factors may be ignored, such as government policies. Future research will need to consider the impact of policy and other factors more comprehensively on P2P lending platform risk identification.Practical implicationsThis study proposes an effective method for investors and regulators to identify the risk factors of P2P lending platforms. The research findings provide valuable insights for promoting government participation in platform management as well as a healthy development of the P2P lending industry.Originality/valueThe paper addresses the factors that influence platform risks to help analyze P2P lending platforms. Prior research has not explored how to identify problematic P2P lending platforms in-depth and is limited by only focusing on either soft information or hard information. It identifies the characteristic factors of identifying problematic platforms and designs a P2P platform risk early warning model.

The paper examines whether the structure of the risk factor disclosure in an IPO prospectus helps explain the cross-section of first-day returns in a sample of Chinese initial public offerings. This paper analyzes the semantics and content of risk disclosure based on an unsupervised machine learning algorithm. From both long-term and short-term perspectives, this paper explores how the information effect and risk effect of risk disclosure play their respective roles. The results show that risk disclosure has a stronger risk effect at the semantic novelty level and a more substantial information effect at the risk content level. A novel aspect of the paper lies in the use of text analysis (semantic novelty and content richness) to characterize the structure of the risk factor disclosure. The study shows that initial IPO returns negatively correlate with semantic novelty and content richness. We show the interaction between risk effect and information effect on risk disclosure under the nature of the same stock plate. When enterprise information transparency is low, the impact of semantic novelty and content richness on the IPO market is respectively enhanced.