| Autor: |
Julia Escobar, Janelle Leslie, Werner Peña, Lucia Martin, Juan José Barrios |
| Rok vydání: |
2021 |
| Předmět: |
|
| DOI: |
10.18235/0003699 |
| Popis: |
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. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
