Title: Artificial neural network to develop loan default predicting model using social media data: a case study of online peer to peer lending

Authors: Taufik Faturohman; Muhammad Abdullah Hamzah Syaiful Mukminin; Sudarso Kaderi Wiryono; Gun Gun Indrayana; Raden Aswin Rahadi; Kurnia Fajar Afgani

Addresses: School of Business and Management, Institut Teknologi Bandung, Bandung, West Java 40132, Indonesia ' School of Business and Management, Institut Teknologi Bandung, Bandung, West Java 40132, Indonesia ' School of Business and Management, Institut Teknologi Bandung, Bandung, West Java 40132, Indonesia ' School of Business and Management, Institut Teknologi Bandung, Bandung, West Java 40132, Indonesia ' School of Business and Management, Institut Teknologi Bandung, Bandung, West Java 40132, Indonesia ' School of Business and Management, Institut Teknologi Bandung, Bandung, West Java 40132, Indonesia

Abstract: Online Peer-to-Peer Lending has been growing rapidly in Indonesia. A system called credit scoring, delineated by a high non-performing financing (NPF) indicator, is considered an important tool used by financial institutions to address concerns and evaluate loan applicants. To enhance credit scoring models, social media data is added to increase the predictability rate on credit scoring models. This paper evaluates credit scoring models using artificial neural networks (ANNs) method with multilayer perceptron (MLP) approach. Inclusion of social media data resulted in increases in the predictability rate by 15.8%, to 98.3%. Our results suggest that social media data addition improves efficiency and healthier portfolios in the alternative financing industry.

Keywords: ANN; artificial neural network; loan default predicting model; social media; online peer-to-peer lending.

DOI: 10.1504/IJMEF.2023.131898

International Journal of Monetary Economics and Finance, 2023 Vol.16 No.3/4, pp.252 - 260

Received: 26 Sep 2021
Accepted: 02 Mar 2022
Published online: 04 Jul 2023 *

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