Temporal feature engineering for agricultural commodity price forecasting in Nigeria: evaluating machine learning, deep learning and time-series approaches

Purpose This study investigates the effectiveness of machine learning, deep learning and traditional time-series approaches for predicting agricultural commodity prices in Nigeria, focussing on improving forecasting reliability through temporal feature engineering and time-aware evaluation using the WFP Nigeria dataset. Design/methodology/approach The study uses 60,566 observations across Nigerian commodity markets (2002–2025). Linear Regression, Random Forest, ARIMA, and LSTM models were evaluated using lag and rolling-average temporal features, with walk-forward validation preserving temporal integrity for realistic assessment. Findings Machine learning models outperformed traditional statistical approaches. Random Forest (R2 = 0.497) exceeded Linear Regression (R2 = 0.465), while ARIMA yielded a negative R2 (−0.259). LSTM achieved its strongest performance for maize (R2 = 0.640) and sorghum (R2 = 0.468), while several highly volatile commodities produced negative R2 values despite extended training and Early Stopping. These results highlight the role of commodity-specific characteristics in price forecasting, with walk-forward validation revealing considerable temporal performance variation. Research limitations/implications The study relies primarily on historical price data and does not incorporate exogenous variables such as weather, inflation, transportation costs or policy interventions. Originality/value This study contributes to the agricultural forecasting literature by integrating temporal feature engineering, chronological validation, walk-forward evaluation, and comparative modelling within a unified framework using a Nigerian commodity price dataset, providing commodity-level evidence on the varying effectiveness of machine learning, deep learning and traditional statistical approaches under realistic forecasting conditions.