We examine the impact of transaction failures on the working of a biometric-enabled payment system introduced in India to facilitate banking by the poor. On average, nearly one-third of transactions fail. However, the proportion of failures decline steeply with user experience. The usage of the...

We ask whether machine learning algorithms improve the efficiency of screening of the loan officers, and thereby help expand access to formal credit. We obtain loan application level data from an Indian bank. To overcome the selective labels problem, we exploit the incentive driven within...