Nowcasting Madagascar's GDP growth: a machine learning approach

Gerzhino Rasolofomanana and Franck Ramaharo

Working Papers from HAL

Abstract: We investigate the predictive power of different Machine Learning models to nowcast Malagasy GDP growth. We trained Lasso, Ridge, Elastic Net, Principal component regression, Random forest, K-Nearest Neighbour and Support Vector Machines algorithms on sixteen Malagasy quarterly macroeconomic and sectorial leading indicators over the period 2007:Q1-2021:Q4, and we used early estimation from the National Institute of Statistics (INSTAT) as a benchmark. We measured the nowcast accuracy of each model by calculating the Root Mean Square Error (RMSE) and the mean absolute percentage error (MAPE). The results show that the machine learning algorithms outperform the traditional time series analysis that are the typical approaches in Malagasy GDP growth modeling. We conclude that Machine Learning models can deliver more accurate and timely nowcasts of Malagasy economic performance, and provide policy makers additional guidance for data-driven decision making.

Keywords: machine learning; nowcasting; Madagascar; economic growth; leading indicator; apprentissage automatique; prévision immédiate; croissance économique; indicateur avancé (search for similar items in EconPapers)
Date: 2023-05-08
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:wpaper:hal-04164610

Access Statistics for this paper

More papers in Working Papers from HAL
Bibliographic data for series maintained by CCSD ().