DEVELOPMENT OF A HYBRID MACROECONOMIC MODEL FOR FORECAST OF ECONOMIC INDICATORS

Abstract

This study proposed a hybrid modelling framework that integrates Random Forest (RF), Vector Error Correction Model (VECM), and Regression Analysis to enhance macroeconomic forecasting in Nigeria. Addressing challenges such as oil price volatility, structural shocks, and sparse high-frequency data, this approach combines RF’s ability to capture non-linear patterns, VECM’s cointegration of non-stationary variables, and Regression’s parametric efficiency through residual correction and ensemble averaging. Using macroeconomic data from 1993–2022, the hybrid model achieved a 23.4% reduction in Mean Absolute Error (MAE) for GDP (from 15.23 to 11.67) and a 28.5% reduction in Root Mean Squared Error (RMSE) (from 20.45 to 14.62), alongside significant improvements for other variables: 17.6% MAE (exchange rate), 15.2% MAE (inflation), 12.1% MAE (unemployment), and 20.3% RMSE (exchange rate), 18.5% RMSE (inflation), 15.6% RMSE (unemployment). The optimized integration weights (  for RF,   for VECM,  for RA in GDP forecasting) highlight machine learning’s dominance in modeling non-linearities, while VECM anchors predictions to long-term equilibria and RA stabilizes parametric relationships. Residual correction and ensemble averaging further reduced systematic biases, as evidenced by tighter error distributions. By bridging machine learning and econometrics, this integrated approach provided policymakers with a robust tool for economic stabilization in resource-dependent economies. While data granularity influenced performance, it highlighted its potential for emerging markets facing structural constraints.