Can Big Data Defeat Traditional Credit Rating?

51 Pages Posted: 11 Jan 2019

See all articles by Jinglin Jiang

Jinglin Jiang

Tsinghua University - PBC School of Finance

Li Liao

Tsinghua University - PBC School of Finance

Xi Lu

BaiRong Financial Information Service Co., Ltd

Zhengwei Wang

Tsinghua University - PBC School of Finance

Hongyu Xiang

Tsinghua University - PBC School of Finance

Date Written: January 6, 2019

Abstract

This paper examines the impact of large-scale alternative data, or big data, on predicting consumer loan delinquency for a traditional lender. Using a unique dataset containing over 3,000 variables, we construct a big data credit score by applying machine learning techniques to deal with high dimensionality and massive missing values. We find that the big data score predicts a borrower’s delinquency likelihood with 18.4% greater accuracy than a lender’s internal rating. The combined model (using both the big data score and internal rating) predicts with 22.6% greater accuracy. Our simulation shows that using the big data score increases the net present value per applicant by $220.

Keywords: Big Data, Fintech, Personal Credit, Alternative Data, Credit Evaluation

JEL Classification: G10, G21, G23

Suggested Citation

Jiang, Jinglin and Liao, Li and Lu, Xi and Wang, Zhengwei and Xiang, Hongyu, Can Big Data Defeat Traditional Credit Rating? (January 6, 2019). Available at SSRN: https://ssrn.com/abstract=3312163 or http://dx.doi.org/10.2139/ssrn.3312163

Jinglin Jiang (Contact Author)

Tsinghua University - PBC School of Finance ( email )

No. 43, Chengdu Road
Haidian District
Beijing 100083
China

Li Liao

Tsinghua University - PBC School of Finance ( email )

No. 43, Chengdu Road
Haidian District
Beijing 100083
China

Xi Lu

BaiRong Financial Information Service Co., Ltd

Zhengwei Wang

Tsinghua University - PBC School of Finance ( email )

No. 43, Chengfu Road
Haidian District
Beijing 100083
China

Hongyu Xiang

Tsinghua University - PBC School of Finance ( email )

No. 43, Chengdu Road
Haidian District
Beijing 100083
China

Register to save articles to
your library

Register

Paper statistics

Downloads
216
rank
138,820
Abstract Views
747
PlumX Metrics
!

Under construction: SSRN citations will be offline until July when we will launch a brand new and improved citations service, check here for more details.

For more information