Automatically Detecting Peer-to-Peer Lending Intermediary Risk—Top Management Team Profile Textual Features Perspective

Abstract

Peer-to-Peer lending is developing quickly around the world as a new E-finance industry, especially in China. Yet fraudulence and business ceasing of Peer-to-Peer Lending Intermediaries (P2P-INTs) occur frequently, making P2P investors facing serious risk. This paper attempts to explore a bridge connecting managerial research with some most advanced natural language processing (NLP) technologies, and examines the risk assessing power of automatic learning text classifiers based on data of hazard status and top management team profile texts of the P2P-INTs. A risk evaluation model named MULTIPLE NLP Integrated Learning Text Classifier (MUN-LETCLA) based on five NLP techniques and meta-learning is proposed. Then risk classification power of the MUN-LETCLA and the single NLP models is assessed. The results show that the proposed model is effective in classifying low-risk and high-risk P2P-INTs. The NLP models can automatically detect the P2P-INTs risk from Top Management Team (TMT) members' working experience, educational background, and TMT composition with a precision level of more than 75%.

Keywords

• Machine learning
• natural language processing (NLP)
• peer-to-peer (P2P) network lending
• risk evaluation
• text analysis