IMF Decides, Machine Learns: An AI Approach to IOs

The project aims to make a major contribution to the literature by creating a comprehensive machine learning (ML) model for predicting the loan size, number of IMF conditions and waivers during program implementation, which complements traditional statistical models by integrating a larger number of variables and providing high accuracy of prediction. The research creates a natural language processing (NLP) tool for automated, fast analysis of the IMF’s Executive Board meeting minutes, which is able to capture elements including individual board member sentiments, alliance between representatives of different countries and G5 stance with high accuracy. Another contribution of the project will be a comprehensive dataset covering IMF programs between 1978-2015, on the various factors influencing IMF program design to the benefit of researchers and practitioners to advance the state-of-the-art through further studies employing ML techniques. Examining IMF behavior when it cooperates with EU institutions, by conducting process tracing on the cases of Romania and Greece, in order to illuminate the causal mechanisms at play, is the fourth contribution the project will deliver.

(with Albana Shehaj & Adrian J. Shin)

Why do international organizations (IOs) favor some countries over others? Previous research has primarily focused on the strategic and special interests of donor states to explain why some countries receive better deals from international organizations. In this project, we highlight migration pressure from the developing world as an important factor that enters into the decision-making calculus of major IO shareholders. Focusing on the International Monetary Fund, the World Bank, and the European Union, we show that countries that pose substantial migration pressure to major donor states of these organizations receive preferential treatment, including larger financial packages and less stringent loan conditions. In addition, we compare and contrast the organizations’ strategies in governing international migration. Using in-depth case studies and novel datasets on loans, conditionality, and fiscal transfers, we demonstrate the important role of international migration in shaping some of the most critical decisions made by the world’s most powerful international organizations.