Artificial Neural Network Backpropagation with Particle Swarm Optimization for Crude Palm Oil Price Prediction

• Published in: Journal of physics. Conference series Vol. 1114; no. 1; pp. 12088 - 12095
• Main Authors: Salman, Nur, Lawi, Armin, Syarif, Syafruddin
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.11.2018
• Subjects: Algorithms; Artificial neural networks; Back propagation; Back propagation networks; Commodities; Economic forecasting; Mathematical models; Neural networks; Optimization techniques; Palm oil; Particle swarm optimization; Plantations; Plants (botany); Prediction models; Pricing; Root-mean-square errors; Vegetable oils
• ISSN: 1742-6588; 1742-6596
• DOI: 10.1088/1742-6596/1114/1/012088

Crude Palm Oil (CPO) is one of the plantation commodities provide the greatest contribution to Indonesia's foreign exchange. Because this plantation is one of the vegetable oil-producing plants with a high economic value. Therefore, the accuracy of the forecasting approaches in predicting the CPO prices is becoming the matter into concerns. This study aims to design a method of forecasting the price level for CPO. Neural Network Backpropagation (NN-BP) has been seen as a successful model in many systems recently. In this paper, we will apply Neural Network Backpropagation with a powerful stochastic optimization technique called Particle Swarm Optimization (PSO) to optimize the weight on NN-BP of Crude Palm Oil commodity price. The proposed method is a prediction model using an algorithm which combining particle swarm optimization (PSO) with Neural Network back-propagation (NN-BP) namely PSO-BP. The experimental results show that the proposed PSO-BP algorithm is better than standard Artificial Neural Network Backpropagation for accurate prediction and error convergence by providing better RMSE values.