文章摘要
Ma Xiaojun,Sha Jinglan,Niu Xueqi.An Empirical Study on the Credit Rating of P2P Projects based on LightGBM Algorithm[J].The Journal of quantitative and technical economics,2018,(5):144-161
基于LightGBM算法的P2P项目信用评级模型的设计及应用
An Empirical Study on the Credit Rating of P2P Projects based on LightGBM Algorithm
  
DOI：
中文关键词: P2P  信用评级  违约率控制  数据清洗  LightGBM算法
英文关键词: P2P  Credit  Control of Default Rate  Data Cleaning  LightGBM Algorithm
基金项目:本文获得国家社科基金项目“高维数据下企业信用评级方法的改进与应用研究”(17BTJ020)、国家自然科学基金项目（71772113）、2017年度辽宁省哲学社会科学规划基金项目(L17BTJ003)的资助。
Author NameAffiliation
Ma Xiaojun Dongbei University of Finance and Economics 
Sha Jinglan Dongbei University of Finance and Economics 
Niu Xueqi Dongbei University of Finance and Economics 
Hits:
Download times:
中文摘要:
      研究目标：在大数据和互联网金融发展的背景下，依据个人信用，有效控制P2P项目的违约率以保证相关金融项目或平台的良好运营。研究方法：本文基于美国P2P平台Lending Club的海量真实交易数据，采用“多观测”与“多维度”两种数据清洗方式，运用2016年微软亚洲研究院提出的机器学习算法LightGBM，兼顾权威性和创新性地对平台内贷款项目的违约风险进行预测，并对不同数据清洗方法的结果进行比较。研究发现：基于多观测的LightGBM算法的预测结果最好，比Lending Club平台历史交易数据算的平均履约率提升了1.28个百分点，可减少约1.17亿美元的违约借款。研究创新：运用不同的数据清洗方式和较为前沿的机器学习算法（LightGBM）预测违约率。研究价值：在LightGBM算法得出违约率影响因素的结果基础上，可以明确Lending Club及广大P2P平台的改进内容和各国在该领域内发展完善的方向。
英文摘要:
      Research Objectives：In the context of big data and Internet finance development，it is effective to control the default rate of P2P projects to ensure good operation of relevant financial projects or platforms according to personal credit.Research Methods：In this paper，based on the P2P platform Lending Club massive real transaction data，we use the ‘multi-observation’ and ‘multi-dimensional’ two kinds of data cleaning method, and predict the risk of default by the 2016 Asian Microsoft LightGBM machine learning algorithms of authority and innovative.Then compare the results of different data cleaning method.Research Findings：LightGBM algorithm based on multi-observations of predicted results is the best.Lending Club platform historical trading data to calculate the average execution rate of 1.28%，can reduce about MYM117 million in loan default.Research Innovations：Using different data cleaning methods and more advanced machine learning algorithm (LightGBM) to predict default rate.Research Value：Based on the result of the influencing factors of default rate，not only the suggestions on development of Lending club and P2P platforms are pointed out，but also the direction of national development in this field.
View Full Text   View/Add Comment  Download reader
Close