An ML Approach to IFIs: Determinants of IMF Lending

ended

The International Monetary Fund (IMF) is frequently argued to be an agent of its most powerful shareholders. Challenging the common belief that strategic allies of the US and/or G5 countries always get better deals from the IMF, whereas it is the IMF staff who has the main leverage over the design of conditionality when low-income countries are borrowing from the Fund, this project will develop a novel framework, drawing upon existing literature on the IMF, in order to present a comprehensive model that takes into account all actors having an impact on IMF program design. The following questions will be at the core of this research: What factors influence the terms of an IMF program? And how do those factors play into shaping the design of the programs? Through creating an original framework, the project will aim to provide an indispensable and extensible tool for international political economy researchers, policymakers, governments and IMF staff to model the program design and implementation process with high predictive power of the outcomes. The project will make a major contribution to the literature by creating a 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 project will also create 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. The research will take on board an eclectic approach, using mixed methods involving ML, NLP, statistical analyses, and process tracing of in-depth case studies (namely Romania and Greece) to account for the variation in the terms of IMF programs.