Can small sample dataset be used for efficient internet loan credit risk assessment? Evidence from online peer to peer lending

被引:21
作者
Yu, Lean [1 ,2 ]
Zhang, Xiaoming [1 ]
机构
[1] Harbin Engn Univ, Sch Econ & Management, Harbin 150001, Peoples R China
[2] Beijing Univ Chem Technol, Sch Econ & Management, Beijing 100029, Peoples R China
基金
中国国家自然科学基金;
关键词
Peer to peer lending; Small sample; Bootstrapping; mega-trend-diffusion; Particle swarm optimization; Virtual sample generation; Internet loan credit risk evaluation;
D O I
10.1016/j.frl.2020.101521
中图分类号
F8 [财政、金融];
学科分类号
0202 ;
摘要
The emerging online peer to peer (P2P) lending platforms have only a small number of samples in the early stage, it is thus unable to conduct an efficient credit risk assessment on internet loan applicants. In order to solve the sample shortage issue, a virtual sample generation (VSG) methodology integrating multi-distribution mega-trend-diffusion (MD-MTD) and particle swarm optimization (PSO) algorithm is proposed for internet loan credit risk evaluation with small samples. The empirical results indicate that the proposed VSG methodology can greatly help to improve performance of the internet loan credit risk evaluation with small sample datasets.
引用
收藏
页数:7
相关论文
共 20 条
  • [1] A PSO based virtual sample generation method for small sample sets: Applications to regression datasets
    Chen, Zhong-Sheng
    Zhu, Bao
    He, Yan-Lin
    Yu, Le-An
    [J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2017, 59 : 236 - 243
  • [2] Analysis of feature selection stability on high dimension and small sample data
    Dernoncourt, David
    Hanczar, Blaise
    Zucker, Jean-Daniel
    [J]. COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2014, 71 : 681 - 693
  • [3] An introduction to ROC analysis
    Fawcett, Tom
    [J]. PATTERN RECOGNITION LETTERS, 2006, 27 (08) : 861 - 874
  • [4] Instance-based credit risk assessment for investment decisions in P2P lending
    Guo, Yanhong
    Zhou, Wenjun
    Luo, Chunyu
    Liu, Chuanren
    Xiong, Hui
    [J]. EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2016, 249 (02) : 417 - 426
  • [5] A distributed PSO-SVM hybrid system with feature selection and parameter optimization
    Huang, Cheng-Lung
    Dun, Jian-Fan
    [J]. APPLIED SOFT COMPUTING, 2008, 8 (04) : 1381 - 1391
  • [6] Kennedy J, 1995, 1995 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS PROCEEDINGS, VOLS 1-6, P1942, DOI 10.1109/icnn.1995.488968
  • [7] A multi-objective approach for profit-driven feature selection in credit scoring
    Kozodoi, Nikita
    Lessmann, Stefan
    Papakonstantinou, Konstantinos
    Gatsoulis, Yiannis
    Baesens, Bart
    [J]. DECISION SUPPORT SYSTEMS, 2019, 120 : 106 - 117
  • [8] Using mega-trend-diffusion and artificial samples in small data set learning for early flexible manufacturing system scheduling knowledge
    Li, Der-Chiang
    Wu, Chih-Sen
    Tsai, Tung-I
    Lina, Yao-San
    [J]. COMPUTERS & OPERATIONS RESEARCH, 2007, 34 (04) : 966 - 982
  • [9] Generating information for small data sets with a multi-modal distribution
    Li, Der-Chiang
    Lin, Liang-Sian
    [J]. DECISION SUPPORT SYSTEMS, 2014, 66 : 71 - 81
  • [10] A genetic algorithm-based virtual sample generation technique to improve small data set learning
    Li, Der-Chiang
    Wen, I-Hsiang
    [J]. NEUROCOMPUTING, 2014, 143 : 222 - 230