Open AccessSOCIAL MEDIA DATA TO DETERMINE LOAN DEFAULT PREDICTING METHOD IN AN ISLAMIC ONLINE PEER TO PEER LENDING
Author(s) -
Hasbila Laila Khilfah,
Taufik Faturohman
Publication year - 2020
Publication title -
journal of islamic monetary economics and finance
Language(s) - English
Resource type - Journals
eISSN - 2460-6146
pISSN - 2460-6618
DOI - 10.21098/jimf.v6i2.1184
Subject(s) - social media , predictability , balanced scorecard , business , credit card , payment , logistic regression , variables , computer science , statistics , marketing , finance , world wide web , mathematics , machine learning
Currently, financial technology is growing rapidly in Indonesia. One of financial technology major type is online peer to peer lending platform. Islamic online peer to peer lending is also emerging. However, credit risk still a major concern for this platform. In order to address this issue, social media assessment is developed. Therefore, in this paper, authors aimed to identify social media variables that could be used as default probability predictors and to determine predictability level by added social media data to the model. Six independent variables consist of social media data and seven control variables from historical payment and demographic data are used to construct credit scorecard and logistic. The result identifies five variables that could be considered and used as default probability predictor which are Posting Frequency in Midnight, Followers, Following, Employment, and Tenor. Interestingly, number of religion accounts followed in Instagram is not a significant variable. Furthermore, the model with selected variables through the combination of demographic, historical payment, and social media data could increase the predictability level by 6.6%.