Analyzing credit risk among Chinese P2P-lending businesses by integrating text-related soft information
作者：
Highlights：
• This thesis examines whether the textual semantic information can help to predict the credit risk of different types of borrowers on the Chinese P2P platform.
• We use the 5P theory and word embedding model to extract semantic features of loan description text from five dimensions.
• The textual semantic feature can significantly improve the predictability of credit evaluation models, and for the new applicant, the promotion effect is more significant.
摘要
•This thesis examines whether the textual semantic information can help to predict the credit risk of different types of borrowers on the Chinese P2P platform.•We use the 5P theory and word embedding model to extract semantic features of loan description text from five dimensions.•The textual semantic feature can significantly improve the predictability of credit evaluation models, and for the new applicant, the promotion effect is more significant.
论文关键词：Credit risk,Chinese P2P,Soft information,5P analysis,Word embedding model
论文评审过程：Received 21 August 2018, Revised 16 December 2019, Accepted 4 February 2020, Available online 12 February 2020, Version of Record 19 February 2020.
论文官网地址：https://doi.org/10.1016/j.elerap.2020.100947
