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%. INDEX TERMS Machine learning, natural language processing (NLP), peer-to-peer (P2P) network lending, risk evaluation, text analysis.

No abstract

Personal Attributes Extraction in Unstructured ChineseText Task is a subtask of The 3rd CIPS-SIGHAN Joint Conference on Chinese Language Processing (CLP-2014). In this report, we propose a method based on the combination of trigger words, dictionary and rules to realize the personal attributes extraction. We introduce the extraction process and show the result of this bakeoff, which can show that our method is feasible and has achieved good effect.

No abstract