Evaluation index of the SVM.

Information asymmetry is widespread in the P2P online lending market, creating an imbalance in the position of lenders and borrowers. This paper aims to expand the process of information exchange between lenders and borrowers by analyzing the link between soft information such as borrowers’ loan descriptions and lending outcomes. Based on the transaction data of the ‘Renrendai’ platform, this paper analyzed the linguistic features and extracted the content of loan descriptions using a latent Dirichlet allocation (LDA) theme model. To further explore the value of loan descriptions in predicting lending success, this paper conducts a prediction study based on a support vector machine model. It is found that: lenders focus on effective information in the loan descriptions, the linguistic complexity affects the transaction, with simple and direct statements being more favorable; the content for building a good personal image of the borrower will significantly contribute to the lending success. In the prediction study section, it is demonstrated that loan descriptions’ language feature indicators can improve prediction accuracy. This paper uncovers the importance of loan descriptions in online lending transactions, which has implications in assisting lenders’ investment judgments, as well as in platform information system improvements.

点对点（Peer-to-Peer，P2P）网络借贷市场普遍存在信息不对称问题，导致出借人与借款人的地位失衡。本文旨在通过分析借款人借款描述等软信息与借贷结果之间的关联，优化出借人与借款人之间的信息交流过程。本文基于人人贷平台的交易数据，对借款描述的语言特征展开分析，并采用潜在狄利克雷分配（LDA）主题模型提取借款描述内容。为进一步探究借款描述在借贷成功预测中的应用价值，本文基于支持向量机（Support Vector Machine, SVM）模型开展了预测研究。研究结果表明：出借人会聚焦借款描述中的有效信息；语言复杂度会对交易产生影响，简洁直白的表述更具优势；旨在塑造借款人良好个人形象的内容，可显著提升借贷成功的概率。在预测研究环节中，本文证实借款描述的语言特征指标能够有效提升预测准确率。本文揭示了借款描述在网络借贷交易中的重要性，该研究成果可为辅助出借人做出投资判断以及完善平台信息系统提供参考依据。