Abstract

Author:
Ibhadon-Agbogidi R.B and Aronu, C. O.

Doi: 10.26480/sfna.02.2025.75.80

This is an open access article distributed under the Creative Commons Attribution License CC BY 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited

Agriculture remains central to Nigeria’s economic development, yet its contribution to Gross Domestic Product (GDP) has fluctuated due to rapid demographic transitions. Understanding how population dynamics influence agricultural performance is critical for designing evidence-based policies. However, existing studies largely rely on traditional econometric models that assume linearity and often fail to capture complex demographic–economic interactions. This study addresses this gap by examining the influence of key demographic variables, Urban Population, Rural Population, Male Population, and Total Population Aged 15– 64, on Agriculture, Forestry, and Fishing Value Added (AFFVA) as a percentage of GDP in Nigeria. The analysis uses secondary data from the World Bank and the United Nations Population Division covering 1981–2023. Two machine-learning tools were applied: the Random Forest (RF) algorithm and a Neural Network (NN) model, both trained and evaluated using Mean Squared Error (MSE) and R-squared (R²) metrics. Results indicate that urbanization negatively affects AFFVA, while the Rural Population and Total Population Aged 15–64 have positive and substantial impacts. The RF model outperformed the NN model, achieving a lower MSE (7.93) and more stable predictions. The study contributes to knowledge by integrating demographic analysis with machine-learning forecasting, demonstrating the superiority of RF in modelling non-linear agricultural dynamics. It concludes that demographic structure remains a critical determinant of agricultural GDP contribution and recommends policies that strengthen rural labour capacity and youth engagement in agriculture.