Fintech Credit Risk Assessment for SMEs: Evidence from China

IMF Working Papers, September 25, 2020

Source details

Promoting credit services to small and medium-size enterprises (SMEs) is a perennial challenge for policy makers globally due to high information costs.
Recent fintech developments may mitigate this problem by leveraging big data or digital footprints on existing platforms; some BigTech firms have extended short-term loans to millions of small firms.
This paper analyzes 1.8 million loan transactions of a leading Chinese online bank to compare:
- the fintech approach: assessing credit risk using big data and machine learning models, and
- the bank approach: assessing credit risk using traditional financial data and scorecard models.

Sample: 1.8 million loan transactions from a leading Chinese online bank.
Comparative approaches:
- Fintech approach: big data and machine learning models.
- Bank approach: traditional financial data and scorecard models.

Predictive performance:
- The fintech approach yields better prediction of loan defaults during normal times and periods of large exogenous shocks, reflecting information and modeling advantages.
Information advantages:
- BigTech’s proprietary information can complement or, where necessary, substitute credit history in risk assessment, allowing unbanked firms to borrow.
Financial inclusion and reach:
- The fintech approach benefits SMEs that are smaller and in smaller cities, hence complementing the role of banks by reaching underserved customers.
Broader implication:
- With more effective and balanced policy support, BigTech lenders could help promote financial inclusion worldwide.

Recognize that big data and machine learning can improve default prediction relative to traditional scorecard models.
Consider policy frameworks that enable BigTech lenders to complement banking services while managing risks, to expand access for unbanked and underserved SMEs.
Design balanced regulation to harness information and modeling advantages of fintech while addressing potential prudential and market-structure concerns.