We introduce unFEAR, Unsupervised Feature Extraction Clustering, to identify economic crisis regimes. Given labeled crisis and non-crisis episodes and the corresponding features values, unFEAR uses unsupervised representation learning and a novel mode contrastive autoencoder to group episodes...

Based on internal data, this paper finds that the capacity development program of the IMF’s Statistics Department has prioritized technical assistance and training to fragile and conflict-affected states. These interventions have yielded only slightly weaker results in fragile states than in...

Over the past two decades, many low-income developing countries have substantially increased openness towards external financing and have received large capital inflows. Using bank-level micro data, this paper finds that capital inflows have been associated with financial deepening through...

The rapid uptake of mobile money in recent years has generated new data needs and growing interest in understanding its impact on broad money. This paper reviews mobile money trends using mobile money data from the Financial Access Survey (FAS) and examines the statistical treatment of mobile...

The application of Deep Reinforcement Learning (DRL) in economics has been an area of active research in recent years. A number of recent works have shown how deep reinforcement learning can be used to study a variety of economic problems, including optimal policy-making, game theory, and...