Multivariate Time Series Forecasting of Crude Palm Oil Price Using Machine Learning Techniques
Open Access
- 14 August 2017
- journal article
- research article
- Published by IOP Publishing in IOP Conference Series: Materials Science and Engineering
- Vol. 226 (1), 012117
- https://doi.org/10.1088/1757-899x/226/1/012117
Abstract
The aim of this paper was to study the correlation between crude palm oil (CPO) price, selected vegetable oil prices (such as soybean oil, coconut oil, and olive oil, rapeseed oil and sunflower oil), crude oil and the monthly exchange rate. Comparative analysis was then performed on CPO price forecasting results using the machine learning techniques. Monthly CPO prices, selected vegetable oil prices, crude oil prices and monthly exchange rate data from January 1987 to February 2017 were utilized. Preliminary analysis showed a positive and high correlation between the CPO price and soy bean oil price and also between CPO price and crude oil price. Experiments were conducted using multi-layer perception, support vector regression and Holt Winter exponential smoothing techniques. The results were assessed by using criteria of root mean square error (RMSE), means absolute error (MAE), means absolute percentage error (MAPE) and Direction of accuracy (DA). Among these three techniques, support vector regression(SVR) with Sequential minimal optimization (SMO) algorithm showed relatively better results compared to multi-layer perceptron and Holt Winters exponential smoothing method.This publication has 17 references indexed in Scilit:
- Correlation and instance based feature selection for electricity load forecastingKnowledge-Based Systems, 2015
- System Dynamics Analysis of the Determinants of the Malaysian Palm Oil PriceAmerican Journal of Applied Sciences, 2015
- Econometric study on Malaysia׳s palm oil position in the world market to 2035Renewable and Sustainable Energy Reviews, 2014
- Does biodiesel demand affect palm oil prices in Thailand?Energy for Sustainable Development, 2013
- Forecasting on Crude Palm Oil Prices Using Artificial Intelligence ApproachesAmerican Journal of Operations Research, 2013
- Price Forecasting Methodology of the Malaysian Palm Oil MarketThe International Journal of Applied Economics and Finance, 2013
- A novel hybridization of artificial neural networks and ARIMA models for time series forecastingApplied Soft Computing, 2011
- An Econometric Analysis of the Link between Biodiesel Demand and Malaysian Palm Oil MarketInternational Journal of Business and Management, 2011
- Machine learning approach for crude oil price prediction with Artificial Neural Networks-Quantitative (ANN-Q) modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Time series forecasting using a hybrid ARIMA and neural network modelNeurocomputing, 2003