Page 194 - Special Topic Session (STS) - Volume 1

STS425 Arifah B. et al.

Modelling long memory stochastic volatility of
crude palm oil price
1
Arifah Bahar 1,2,* , Shaymaa Mustafa , Kho Chia Chen, Haliza Abd Rahman ,
2
Nur Arina BazilahAziz , Zaitul Marlizawati Zainuddin , Zainal Abdul Aziz
1,2
1,2
1,2
1 Department of Mathematical Sciences, Faculty of Science, Universiti Teknologi Malaysia
2 UTM Centre for Industrial and Applied Mathematics (UTM-CIAM), Ibnu Sina Institute for
Scientific and Industrial Research (ISI-SIR) Universiti Teknologi Malaysia

Abstract
Crude palm oil (CPO) is one of the largest commodity for export in Malaysia.
Forecasting its future price plays an important role in planning various
investment and business activities for optimal resource allocation. However,
this task is not a trivial one as it possesses long memory stochastic volatility.
This study will handle this issue by using fractional Ornstein-Uhlenbeck (fOU)
process to describe the time series of the CPO price so that the degree of its
persistency can be estimated. Model will be constructed with long memory
stochastic volatility (LMSV) based on 12 years daily CPO prices. The least
square estimator (LSE) and quadratic generalised variations (QGV) method will
be used to estimate the drift and diffusion coefficient of the volatility process
respectively. The long memory parameter is estimated by the detrended
fluctuation analysis (DFA) method. Small values of root mean square errors
(RMSE) for the model and mean absolute percentage errors (MAPE) indicate a
good forecast for future CPO price.

Keywords
Crude palm oil; fractional Ornstein-Uhlenbeck; long memory stochastic
volatility; least square estimator; quadratic generalised variations.

1. Introduction
An accurate forecasting on crude palm oil (CPO) prices is one of the most
important economic indicators in the world. All the participants in this industry
including the producers, marketers, Policy-makers, consumers and financial
participants monitor the CPO price behavior (Charles and Darné, 2014). There
are more than 150 countries around the world consuming it (Rahim et al.,
2018). The raising of the demand of CPO in last decades, especially in
developing countries led to a continuous increase and volatile in the CPO
prices (Rahim et al., 2018). This volatility and instability in trajectories and
behavior of the prices is considered critical particularly in dealing with
uncertainties and risks for the oil palm business (Charles and Darné, 2014).
Malaysia is one of the biggest exporters of CPO in the world and it is the
leader of the production of the world palm oil (Arshad and Zainalabidin, 1994).

183 | I S I W S C 2 0 1 9