基于TF-IDF算法的P2P贷款违约预测模型  

P2P loan default prediction model based on TF-IDF algorithm

作　　者：章宁[1] 陈钦 ZHANG Ning;CHEN Qin(School of Information,Central University of Finance and Economics,Beijing 100081,China;IT Department,China Development Bank Financial Leasing Company Limited,Shenzhen Guangdong 518038,China)

机构地区：[1]中央财经大学信息学院,北京100081 [2]国银金融租赁股份有限公司信息化管理部,广东深圳518038

出　　处：《计算机应用》2018年第10期3042-3047,共6页journal of Computer Applications

基　　金：国家重点研发计划项目(2017YFB1400701)~~

摘　　要：针对目前P2P贷款违约预测模型受限于借贷双方信息不对称性,未考虑投资人之间差异性的问题,提出了基于信息检索词频-逆文本频率(TF-IDF)算法的P2P贷款违约预测模型。首先以投资效用理论为基础,利用投资人历史投资收益率、贷款利率出价等信息,建立基于投资人效用的贷款违约预测模型;然后,借鉴信息检索TF-IDF算法,构造投资人逆向投资比例因子,对投资人差异性进行量化度量,优化模型中投资人权重计算因子。实验结果表明,该模型预测准确度与其他模型相比平均提高了6%左右,并在不同的测试数据集上都保持最优。Concerning that current P2P loan default prediction models are limited by the information asymmetry of lenders and borrowers,and do not take differences between loan lenders into account,a P2P loan default prediction model based on Term Frequency-Inverse Document Frequency(TF-IDF)algorithm of information retrieval was proposed.Firstly,based on the investment utility theory,a loan default prediction model was established by using the information such as lender s historical investment profit rate and loan bid interest rate.Secondly,referred to TF-IDF algorithm of information retrieval,loan lender s reverse investment scale factor was constructed to quantify the lender s differences,and the weight factor in the model were optimized.Experimental results show that the prediction effect of this model is better than those of other models on different data sets,its prediction accuracy increases by an average of 6%compared with other models.

关 键 词：贷款违约预测 效用理论 信息检索 词频逆文本频率 个人对个人借贷 曲线下面积 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TP391.1[自动化与计算机技术—控制科学与工程]