Nowcasting to Predict Economic Activity in Real Time: The Cases of Belize and El Salvador

Abstract

This paper presents machine learning models fitted to nowcast or predict quarterly GDP activity in real time for Belize and El Salvador. The initiative is part of the Inter-American Development Bank's (IDB) ongoing effort to develop timely economic monitoring tools following the shock of the Covid-19 pandemic. Nowcasting techniques offer an effective tool to fill the information gap between the end of a quarter and the official publication of macroeconomic indicators that are generally lagged by 60 to 90 days, by exploiting the availability of other indicators that are published more frequently. The results show that machine learning techniques can produce accurate quarterly GDP forecasts for two structurally different economies within economic contexts marked by extreme degrees of volatility and uncertainty at both the national and international levels. Because the calibration of nowcasting exercises is a dynamic process that is refined over time, at the IDB, we trust that this document will help support the ongoing work of the governments and statistical agencies of Belize and El Salvador in securing better economic forecasts to inform agile policy decisions.

Nowcasting Madagascar's real GDP using machine learning algorithms

“…During the prediction phase, the individual tree predictions are averaged to obtain the final output. This diverse ensemble architecture makes RFR particularly adept at capturing the complex, non-linear dynamics of economic data, leading to robust GDP predictions [5,28,38,42,62,68].…”

“…Machine Learning algorithms have now become a valuable tool in economic modelling, demonstrating remarkable efficacy in the challenging task of nowcasting and forecasting GDP across diverse global contexts. This effectiveness is evident in advanced economies (e.g., Canada [54], China [67,69], Finland [26], Italy [21], Netherlands [42], New Zealand [55,56,60], South Africa [17], Sweden [40], USA [31,45], multiple European countries [23]), emerging markets and developing countries (e.g., Albania [66], Bangladesh [32], Belize and El Savador [5], Brazil [57], Egypt [1], Georgia [46], India [28], Indonesia [62], Lebanon [64], Malaysia [38], Peru [63])). Moreover, Machine learning algorithms are also proved to be very competitive with respect to standard econometric methods.…”