Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/336403 
Authors: 
Year of Publication: 
2024
Citation: 
[Journal:] Latin American Journal of Central Banking (LAJCB) [ISSN:] 2666-1438 [Volume:] 5 [Issue:] 3 [Article No.:] 100126 [Year:] 2024 [Pages:] 1-25
Publisher: 
Elsevier, Amsterdam
Abstract: 
This research introduces an innovative GDP nowcasting strategy tailored for developing countries, specifically addressing challenges related to limited data timeliness. The study centers on Bolivia, where the official monthly indicator of economic growth is released with a substantial delay of up to six months. The proposed nowcast estimates effectively narrow this gap from six to two months. This advancement is achieved through the integration of machine learning techniques with data comprising indicators from traditional sources and statistics derived from satellite imagery. The robustness of this approach is rigorously validated using various criteria, including performance comparisons with conventional econometric methods and sensitivity assessments to different feature sets. Beyond enhancing the understanding of Bolivia's economic dynamics, this research establishes a framework for analogous analyses in regions grappling with information availability challenges.
Subjects: 
Nowcasting
Machine learning
Remote sensing
Economic growth forecast
JEL: 
C10
C14
C22
C53
C80
E17
Persistent Identifier of the first edition: 
Creative Commons License: 
cc-by-nc-nd Logo
Document Type: 
Article

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.