Abstract
Pepper is the most used spice and flavoring agent in the food industry. Sri Lanka is the fifth largest exporter of pepper in the world. Variations in export income of pepper is a huge matter for farmers, consumers, investors and policy makers in the country. Hence an accurate forecast of export income is extremely important. This study presents a time series modelling approach for forecasting the income of pepper exports in Sri Lanka. Two different models are adopted: deterministic decomposition model which is built decomposing the trend, seasonality and the random variations and Seasonal Auto Regressive Integrated Moving Average (SARIMA) which belongs to the stochastic class of models. The data used in this study are monthly export income of pepper in Sri Lanka from January 2000 to December 2018. Among the two types of models, deterministic decomposition model with Mean Absolute Error (MAE) of 4.36 has a strong potential in forecasting the income of pepper exports in Sri Lanka. As the forecasts from the model shows an increasing pepper export market which will need a higher production of pepper, the government can improve the awareness of farmers about the requirements of pepper in export market by providing infra-structure facilities.