Forecasting Coconut Yield: A Comparative Study between the Use of Traditional Forecasting and Feed Forward Back Propagation Artificial Neural Network

Eric John  G. Emberda,; Den Ryan  L. Dumas,; Timothy Pierce  M. Rentillo,

Forecasting Coconut Yield: A Comparative Study between the Use of Traditional Forecasting and Feed Forward Back Propagation Artificial Neural Network

Eric John G. Emberda | Den Ryan L. Dumas | Timothy Pierce M. Rentillo

Abstract:

This study compared the use of Linear Regression and Feed Forward Backpropagation Artificial Neural Network (ANN) in forecasting the coconut yield and copra yield of a selected area in Davao region. Raw data were gathered from the Philippine Coconut Authority, Davao Research Center. An ANN model was created and tested repeatedly to the best combination of nodes. Accuracy of the forecast between the two methods was compared by looking at the mean square error and the standard error for variable x and y. Results showed that the use of Feed Forward Back Propagation Artificial Neural Network gives better accuracy of the forecast data.