Title: Evaluation of borrower's credit of P2P loan based on adaptive particle swarm optimisation BP neural network

Authors: Sen Zhang; Yuping Hu; Chunmei Wang

Addresses: Information Institute, Guangdong University of Finance and Economics Guangzhou, No. 21, Luntou Road, Haizhu District, Guangzhou, 510320, Guangdong, China ' Information Institute, Guangdong University of Finance and Economics Guangzhou, No. 21, Luntou Road, Haizhu District, Guangzhou, 510320, Guangdong, China ' College of Internet Finance and Information Engineering, Guangdong University of Finance, Guangzhou, 510521, Guangzhou, China

Abstract: Personal credit assessment is the main method to reduce the credit risk of P2P online loans. In this paper, after the adaptive mutation operator is used to reinitialise the particles with a certain probability and the global search capability of the particle swarm optimisation algorithm is used to optimise the weights and thresholds of the BP neural network, a method which adopts adaptive mutation particle swarm combined with BP neural network model is proposed to evaluate borrower's credit of P2P network loan. Result of simulation experiment shows that AMPSO-BP neural network model has higher prediction accuracy, smaller error variation range, better fitting ability and robustness than the BP neural network model in P2P network loan borrower credit evaluation applications.

Keywords: P2P network loan; personal credit; BP neural network; particle swarm algorithm; adaptive mutation.

DOI: 10.1504/IJCSE.2019.100240

International Journal of Computational Science and Engineering, 2019 Vol.19 No.2, pp.197 - 205

Received: 14 Apr 2018
Accepted: 19 Jul 2018

Published online: 17 Jun 2019 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article