HYBRID MODELING OF NIGERIAN CRUDE OIL PRICES UNDER STRUCTURAL BREAKS AND VOLATILITY

Abstract

Accurate forecasting of crude oil prices is vital for robust economic planning, risk management, and policy
formulation in Nigeria. This study introduces an innovative hybrid forecasting framework that integrates the
statistical strengths of FB Prophet, ARIMA, and SARIMA models with machine learning techniques. The proposed
framework is designed to capture the complex dynamics of Nigeria’s daily crude oil prices, including long-term
trends, seasonal patterns, non-linear behaviors, volatility clustering, and structural breaks. The analysis utilizes a
longitudinal dataset of daily prices spanning from January 1986 to December 2025. Empirical results reveal
significant non-linearity, heavy-tailed distributions, and multiple structural breaks triggered by global shocks, such
as the 2014–2016 price collapse and the COVID-19 pandemic. Stationarity tests indicate that while price levels are
non-stationary, the return series remain stationary, justifying the application of integrated econometric models. The
ARIMA and SARIMA components deliver superior short-term accuracy, whereas the FB Prophet model excels at
identifying medium- to long-term trajectories. By synthesizing these methodologies, the hybrid model maintains the
rigor of traditional statistical approaches while enhancing reliability amidst heightened volatility. The resulting
forecasts offer high statistical precision and practical utility for trend and risk analysis. These insights provide a
critical foundation for investors, policymakers, and stakeholders dedicated to bolstering Nigeria’s economic
resilience in the global market.