This IMF blog post from the IMF considers one pathway for protecting the global banking system amid the pandemic. Pointing to the experience of the 2008 crisis and recovery, the authors recommend requiring transparent loss reporting, relying on capital and liquidity buffers to support continued lending, and encouraging loan modification.

This paper provides a nontechnical overview of common machine learning algorithms used in underwriting credit. It provides a review – including strengths and weakness – of common machine learning techniques in credit underwriting, including tree-based models, support vector machines, and neural networks. The paper also considers the financial inclusion implications of machine learning, nontraditional data, and fintech.