Research on coffee exports to main destination countries is important because it provides an in-depth understanding of the markets that are the main focus. This allows governments and businesses to allocate resources efficiently and design appropriate marketing strategies. In addition, this research provides a strong basis for the government in formulating coffee export policies. By monitoring the development of coffee exports to main destination countries, Indonesia can be better prepared to face changes in global market demand and take appropriate steps in responding to market dynamics. . This research will use the Conjugate Gradient Fletcher-Reeves algorithm, which is one of the algorithms of Artificial Neural Networks. The research was analyzed using 3 architectural models, including: 5-5-1, 5-10-1, and 5-15-1. As a result, the 5-5-1 model was selected as the best model, with the highest accuracy of 94% and the lowest MSE of 0.00500142. Higher than the accuracy of the 5-10-1 model which is only 83% with MSE 0.05058359, and 78% accuracy with MSE 0.01975643 on the 5-15-1 model. Based on the estimation results regarding the development of coffee exports according to main destination countries using the 5-5-1 model, the conclusion that can be drawn is that there will likely be a decline in the level of coffee exports to main destination countries in 2024.
Copyrights © 2024