Time series based forecasting for crude palm oil price utilizing neural network algorithms

Abstract

This study aims to present time series-based forecasting for Malaysian crude palm oil prices using neural network algorithms. Daily prices of soy bean oil and currency exchange rates are tested as input features, in addition to crude palm oil prices. Efforts are focused on finding the optimal network structures for the modelling of crude palm oil price forecasting. Neural network structures with an appropriate selection of input and hidden nodes are tested. The results demonstrate that the number of input features and hidden nodes significantly impact crude palm oil price predictions.