A Deep Learning Approach for Loan Default Prediction Using Imbalanced Dataset

被引:3
作者
Owusu, Ebenezer [1 ]
Quainoo, Richard [1 ]
Mensah, Solomon [1 ]
Appati, Justice Kwame [1 ]
机构
[1] Univ Ghana, Accra, Ghana
关键词
Adaptive Synthetic (ADASYN) algorithm; Deep neural network; Imbalanced dataset; Loan-default; Prediction;
D O I
10.4018/IJIIT.318672
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Lending institutions face key challenges in making accurate predictions of loan defaults. Large sums of money given as loans are defaulted and this causes a substantial loss in business. This study addresses loan default in online peer-to-peer lending activities. Data for the study was obtained from the online lending club on the Kaggle platform. The loan status was chosen as the dependent variable and was classified discretely into "default" and "fully paid" loans. The dataset is preprocessed to eliminate all irrelevant instances. Due to the imbalanced nature of the dataset, the adaptive synthetic (ADASYN) oversampling algorithm is used to balance the data by oversampling the minority class with synthetic data instances. Deep neural network (DNN) is used for prediction. A prediction accuracy of 94.1% is realized and this emerged as the highest score from several trials with variations in batch sizes and epochs. The result of the study clearly shows that the proposed procedure is very promising.
引用
收藏
页数:16
相关论文
共 20 条
[1]   Comparing Oversampling Techniques to Handle the Class Imbalance Problem: A Customer Churn Prediction Case Study [J].
Amin, Adnan ;
Anwar, Sajid ;
Adnan, Awais ;
Nawaz, Muhammad ;
Howard, Newton ;
Qadir, Junaid ;
Hawalah, Ahmad ;
Hussain, Amir .
IEEE ACCESS, 2016, 4 :7940-7957
[2]   Wide and deep learning for peer-to-peer lending [J].
Bastani, Kaveh ;
Asgari, Elham ;
Namavari, Hamed .
EXPERT SYSTEMS WITH APPLICATIONS, 2019, 134 :209-224
[3]   An empirical comparison on state-of-the-art multi-class imbalance learning algorithms and a new diversified ensemble learning scheme [J].
Bi, Jingjun ;
Zhang, Chongsheng .
KNOWLEDGE-BASED SYSTEMS, 2018, 158 :81-93
[4]  
Ceballes-Serrano C. C., 2012, 2012 XVII Symposium of Image, Signal Processing, and Artificial Vision (STSIVA 2012), P218, DOI 10.1109/STSIVA.2012.6340585
[5]   SMOTEBoost: Improving prediction of the minority class in boosting [J].
Chawla, NV ;
Lazarevic, A ;
Hall, LO ;
Bowyer, KW .
KNOWLEDGE DISCOVERY IN DATABASES: PKDD 2003, PROCEEDINGS, 2003, 2838 :107-119
[6]  
Chen YQ, 2018, INT CONF MACH LEARN, P240, DOI 10.1109/ICMLC.2018.8526936
[7]   A Dynamic Default Prediction Framework for Networked-guarantee Loans [J].
Cheng, Dawei ;
Zhang, Yiyi ;
Yang, Fangzhou ;
Tu, Yi ;
Niu, Zhibin ;
Zhang, Liqing .
PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM '19), 2019, :2547-2555
[8]  
Turiel JD, 2019, Arxiv, DOI arXiv:1907.01800
[9]   Financial system modeling using deep neural networks (DNNs) for effective risk assessment and prediction [J].
Duan, Jing .
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 2019, 356 (08) :4716-4731
[10]  
Feis A., 2016, P2P LOAN SELECTION