TY - GEN
T1 - Analysis and prediction of P2P online lending platform - Based on binary logistic regression model
AU - Zhang, Yuanyuan
AU - Shen, Yuelin
N1 - Funding Information:
This project is in part supported by National Science Foundation of China (Grant Number: 71371114).
PY - 2017
Y1 - 2017
N2 - This paper uses 17 indicators to analyze the critical factors that affect the P2P online lending platforms based on a binary logistic regression model. It shows that the problematic P2P online lending platforms are closely related to four indicators: the average interest rate, the top ten borrowers in terms of the repayment amount, the operating duration, and the top ten investors to receive the repayments. The accuracy of the regression model is up to 73% to predict whether the P2P network lending platform will be in a problem.
AB - This paper uses 17 indicators to analyze the critical factors that affect the P2P online lending platforms based on a binary logistic regression model. It shows that the problematic P2P online lending platforms are closely related to four indicators: the average interest rate, the top ten borrowers in terms of the repayment amount, the operating duration, and the top ten investors to receive the repayments. The accuracy of the regression model is up to 73% to predict whether the P2P network lending platform will be in a problem.
KW - Binary logistic regression model
KW - Online loan
KW - Peer-to-peer
KW - Problematic platform
UR - http://www.scopus.com/inward/record.url?scp=85027862434&partnerID=8YFLogxK
M3 - Conference Proceeding
AN - SCOPUS:85027862434
T3 - 2017 7th International Workshop on Computer Science and Engineering, WCSE 2017
SP - 1289
EP - 1295
BT - 2017 7th International Workshop on Computer Science and Engineering, WCSE 2017
PB - International Workshop on Computer Science and Engineering (WCSE)
T2 - 2017 7th International Workshop on Computer Science and Engineering, WCSE 2017
Y2 - 25 June 2017 through 27 June 2017
ER -