Evaluating Forecasts in Times of Financial Turmoil

Abstract

External sector surveillance and stabilization are core missions of the International Monetary Fund (IMF). Since 1992, the IMF approved over 600 crisis country loan programs, conditional on reforms and performance targets that are contingent on IMF crisis assessments and recovery forecasts. The literature evaluating IMF crisis forecasts has primarily focused on GDP, inflation, and fiscal budgets, but IMF programs often originate with balance of payments crises. Our evaluation of IMF imports/exports/exchange rates in crisis countries reveals a surprising dichotomy: import forecasts are largely efficient and unbiased, while exports and exchange rate forecasts exhibit substantial biases and inefficiencies. We show forecast errors in the full sample are driven by deeply flawed IMF forecasts for LICs in crisis. Fixed exchange rate LICs (predominantly African franc zone countries) receive systematically inefficient import forecasts. Exchange rate forecasts for LICs with flexible exchange rates are so inefficient, they cannot outperform a naive random walk, and over 30 percent of the forecasts cannot match the exchange rate’s directional movement during the first year of the recovery. Examining the sources of biases and inefficiencies, we highlight effects of conditionality and geopolitics that were not fully accounted for in IMF forecasts, specifically those relating to arrears (domestic and foreign), fiscal finance (balance and credit limits), policy reforms (trade and government), (civil) wars, and elections.