Forecasting on Crude Palm Oil Prices Using Artificial Intelligence Approaches

Abstract

An accurate prediction of crude palm oil (CPO) prices is important especially when investors deal with ever-increasing risks and uncertainties in the future. Therefore, the applicability of the forecasting approaches in predicting the CPO prices is becoming the matter into concerns. In this study, two artificial intelligence approaches, has been used namely artificial neural network (ANN) and adaptive neuro fuzzy inference system (ANFIS). We employed in-sample forecasting on daily free-on-board CPO prices in Malaysia and the series data stretching from a period of January first, 2004 to the end of December 2011. The predictability power of the artificial intelligence approaches was also made in regard with the statistical forecasting approach such as the autoregressive fractionally integrated moving average (ARFIMA) model. The general findings demonstrated that the ANN model is superior compared to the ANFIS and ARFIMA models in predicting the CPO prices.

Multivariate Time Series Forecasting of Crude Palm Oil Price Using Machine Learning Techniques

“…Soybean oil has been a long term competitor of CPO [10]. Past studies [8] [11] suggested that there is a short and long run relationship between CPO price and soybean oil price. Our analysis shed some light on how the changes in soybean oil price movement affect the movement of CPO price.…”

“…Khin [15] utilized Vector Error Correction Method (VECM) to analyze the relationship between spot and futures prices in forecasting the CPO price. Even though statistical models were widely used for solving time series forecasting problems, recent trend showed machine learning techniques outperformed the classical statistical methods [8].…”

Optimization of Technical Analysis in the Palm Oil Marketing Strategy: Daily Pricing Model for 30 Days Transactions

“…Hasil-hasil penelitian terkait peramalan harga minyak kelapa sawit berbasis analisis univariate maupun multivariate time series hingga model ekonometrika relatif telah banyak dilakukan. Beberapa penelitian terkait, antara lain penelitian Kanchymalay et al (2017), Ariff et al (2015), Ahmad et al (2014), Ahmed dan Shabri (2014), Kantaporn et al (2013), Khin et al (2013), Karia (2013), Karia dan Bujang (2011), dan Kurniawan (2011). Data basis yang menjadi unit ramalan pada analisis univariate maupun multivariate time series pada umumnya adalah harga bulanan dan sedikit yang berbasis data harian serta berupa peramalan post-ante untuk sebuah periode tertentu.…”

Crude Palm Oil Prediction Based on Backpropagation Neural Network Approach

“…Numerous methods are used in order to obtain accurate prediction results such as statistical methods (i.e., ARMA, ARIMA, SARIMA, and ES) and intelligent computing methods (i.e., fuzzy logic, neural network) [4][5] [6] [7]. A research by [8] used SARIMA method to predict crude palm oil, in Terengganu, Malaysia.…”