Big tech credit score and default risk --Evidence from loan-level data of a representative microfinance company in China

Using a unique loan-level dataset from a representative microfinance company in China, this paper investigates the information spillover effect of big tech credit scores on microloan risk management. We analyze a quasi-natural experiment where the microfinance company integrated big tech credit scores into its loan decision-making process. Our findings indicate that incorporating fintech information into risk assessments significantly lowers the default rate for new borrowers compared to existing ones. This effect is more pronounced for borrowers with insufficient collateral, higher loan demand, and medium risk levels, as well as for branches with higher historical default rates. Additionally, we observe a slight reduction in approved loan amounts for borrowers with medium risk levels, suggesting that big tech information contributes to more prudent loan decisions in microfinance.