ABSTRACT:
While Peer-to-Peer (P2P) lending is rapidly growing, it is also accompanied by high credit risk due to information asymmetry. Besides conventional hard information, soft information also enters into the lending decision process. The descriptive loan texts submitted by borrowers have great potential for exploiting useful soft factors, but also pose great challenges due to the semantic sensitivity to context and the complexity of content representation. We propose a novel text mining method for automatically extracting semantic soft factors from descriptive loan texts. The method maps terms to an embedding space, assembles semantically related terms together into semantic cliques, and then defines semantic soft factors corresponding to the semantic cliques. Empirical evaluation shows that the extracted semantic soft factors contributed to significant improvement on credit risk evaluation in terms of both discrimination performance and granting performance. This work advances our knowledge of soft information indicative of a borrower’s credit risk.
Key words and phrases: P2P lending, descriptive loan text, credit risk evaluation, text mining, soft information, semantic soft factor, online lending