Application of the Holt-Winters Multiplicative Method to Predict Cayenne Pepper Production in Riau Province

Abstract

Production forecasting in the agricultural sector is an important component in the planning and decision-making process, especially for commodities with high levels of demand such as cayenne pepper. This study aims to predict the amount of cayenne pepper production in Riau Province by applying the Holt-Winters Multiplicative method. The selection of this method is based on its ability to process time series data that has seasonal patterns and trends that change proportionally to the data level. The data used in this study is secondary data sourced from the Riau Province Food, Food Crops, and Horticulture Office for the period from 2022 to 2024. The analysis stage includes data exploration, determination of the initial smoothing value for levels, trends, and seasonality, adjustment of smoothing parameters (α, β, γ), and evaluation of model performance using MAPE, MAD, and MSE error measures. Based on the results of the analysis, it shows that the Holt-Winters Multiplicative model produces a MAPE value of 11%, which indicates that the model has a good level of accuracy. Therefore, this method can be used as a supporting tool in planning the production and distribution of cayenne pepper in Riau Province.