Application of Some Forecasting Model for Predicting Prices on Agricultural Commodities in Federal Capital Territory Abuja

Abstract

This study evaluates the performance of various forecasting models in predicting the prices of agricultural commodities in the Federal Capital Territory Abuja. The aim is to identify the most effective model for forecasting food prices and analyze the trends over a seven year period. Key forecasting models applied include Exponential Moving Average (EME), Seasonal Autoregressive Integrated Moving Average (SARIMA), Exponential Smoothing Average (EMA), and Support Vector Regression (SVR). Model performance was assessed using average Mean Absolute Error (MAE), Mean Square Error (MSE), and Root Mean Square Error (RMSE). Results showed that Exponential Moving Average Model outperformed others with lowest average MAE (94.05), MSE (66895.17), and RMSE (219.04). The study also identified consistent in food prices over the forecasted five-year period (2024-2028) for key commodities like rice, maize, soya beans, yam and gari. The forecasted price of milled rice remained stable at 992.42 Naira while yam maintain a consistent price 3320. 59 Naira thorough the period. The findings suggest that the Exponential Moving Average model is a robust tool for predicting agricultural commodity prices in FCT, enabling better decision-making and resources allocation in the sector