Forecasting The Price of Red Bird's Eye Chili in Southeast Sulawesi Province Containing Outlier Data Using ARIMA Method with Iterative Procedure

Abstract

The price of red bird's eye chili in Southeast Sulawesi Province often experiences fluctuations that are detrimental to farmers. This study aims to forecast the price of red bird's eye chili using the ARIMA model and to correct outliers that affect the model’s accuracy. The ARIMA(2,1,1) model was selected as the best-fitting model after detecting and correcting four innovational outliers (IO). The correction process resulted in a decrease in the Mean Squared Error (MSE) from 50,602,363 to 38,245,864. The 20-week-ahead forecast indicates a downward trend in prices, with increasingly stable prediction intervals. This method proves effective in improving model accuracy and providing more reliable information for decision-making.