This article investigates the determinants of bank loan survival time in an emerging economy for 'micro', 'small' and 'medium'-sized enterprises. We use proprietary data from the Central Bank of Mexico for approximately 1.5 million company loans between January 2010 and May 2017. Our results show that firm' characteristics at the time of loan origination, and lagged macroeconomic factors have a significant impact on the loan survival times. Further tests on model validation show that our fitted survival model performs reasonably well in out of sample forecasts.

This paper investigates whether three microeconomic loan characteristics are sources of loan default clustering in the Mexican banking sector by employing survival analysis with frailty. Using a large sample of bank loan level data granted to micro, small and medium sized firms from January 2010 to 2018, we test whether classifying loans by the bank's systemic importance, industry or at individual firm level enhances the predictions of loans defaults. Our results show that loans granted by Domestic Systemically Important Banks contribute to the default clustering in micro and small firm loans. This is due to aggregate default rate levels and clusters that are large for these firms loans compared with loans provided to medium-sized firms. These findings have important implications for bank's expected loss management related to the correlated loan default risk