loading page

Predicting gross domestic product using the ensemble machine learning method.
  • +10
  • M.D. Adewale,
  • D.U. Ebem,
  • O. Awodele,
  • E.M. Aggrey,
  • E.A. Okechalu,
  • R.E. Donatus,
  • K.A. Olayanju,
  • A.F. Owolabi,
  • J.U. Oju,
  • O.C. Ubadike,
  • G.A. Otu,
  • U.I. Muhammed,
  • O.P. Oluyide
M.D. Adewale
National Open University of Nigeria

Corresponding Author:[email protected]

Author Profile
D.U. Ebem
University of Nigeria
Author Profile
O. Awodele
Babcock University Babcock Business School
Author Profile
E.M. Aggrey
National Open University of Nigeria
Author Profile
E.A. Okechalu
National Open University of Nigeria
Author Profile
R.E. Donatus
National Open University of Nigeria
Author Profile
K.A. Olayanju
National Open University of Nigeria
Author Profile
A.F. Owolabi
National Open University of Nigeria
Author Profile
J.U. Oju
National Open University of Nigeria
Author Profile
O.C. Ubadike
National Open University of Nigeria
Author Profile
G.A. Otu
National Open University of Nigeria
Author Profile
U.I. Muhammed
National Open University of Nigeria
Author Profile
O.P. Oluyide
National Open University of Nigeria
Author Profile

Abstract

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.