Predicting gross domestic product using the ensemble machine learning method.

Résumé fourni par la source

Researchers have proposed including more indicators in Gross Domestic Product (GDP) prediction. This study developed a predictive model for the GDP of Nigeria by considering indicators such as healthcare spending, net migration, population, life expectancy, electricity access, and individuals using the internet in Nigeria. The study utilised a dataset of GDP and relevant economic and non-economic indicators from 2000 to 2021. Machine learning algorithms, including Random Forest Regressor, XGboost Regressor, and Linear Regression Analysis, were used to build predictive models and evaluate their performance. The results show that all the independent variables highly correlate with GDP and that the Random Forest Regressor outperforms the other algorithms in GDP prediction. The Random Forest Regressor with R 2 of 0.96 and Mean Absolute Error (MAE) of 24.29 is suitable for predicting Nigeria’s GDP in this context and that initiatives to improve healthcare, electricity access, internet access, and population could bolster the country’s economic growth.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.