Forecasting the Performance of PT Pertamina's Petrochemical
Products During the Covid-19 Pandemic Era
WALJIYANTO*, M. AL MUSADIEQ, EDY YULIANTO, YUSRI ABDILLAH
Brawijaya University, Veteran Street, Malang INDONESIA
Corresponding Author Email: waljiyanto@student.ub.ac.id
Abstract: The industrial sector is a vital sector in economic development and growth in Indonesia. The
industrial sector is also a dominating energy user. This research purposed to examine projected demand
for petrochemicals after the COVID-19 pandemic. This study was a quantitative research with the
exploratory and descriptive approach; spesifically using forecasting methods (Vector Autoregressive
(VAR)). VAR is a multivariate forecasting model used to build a forecasting system from interrelated
time series data. The results of the analysis prediction shows that the demand for petrochemicals will
increase starting in 2021. The risk impact caused by COVID -19 is estimated to be more significant,
with Petrochemical products are Aromatic 45%, Bitumen 45%, and Special Chemical 41%. The effect
of COVID-19 in reducing the economy causes the industry to reduce the amount of production.
Keywords: Petrochemicals, Vector Autoregressive, COVID-19; Pandemic; Forecasting
Received: October 29, 2022. Revised: May 24, 2023. Accepted: June 24, 2023. Published: July 18, 2023.
1. Introduction
Nowadays, COVID-19 pandemic is
rapidly widespread in the world, especially in
Indonesia. This virus first spread in the
Wuhan area, China and made the Chinese
government impose a lockdown policy or
restriction of entry to Wuhan. As of March
27, 2020, according to Merdeka.com, there
were a total of 1,046 more people who tested
positive for COVID-19. The impact of the
Indonesian business world began. Many
business processes have been disrupted due to
COVID-19, which has spread rapidly.
The raging spread of COVID-19 is
transmitted through droplets or fluids that
come out when a person with COVID-19
sneezes and coughs. The COVID-19 virus
will immediately be transmitted to
individuals with weak immune systems then
will have an incubation period of 14 days in
the body. Within 14 days, victims of COVID-
9 infection may experience coughs, dizziness
and difficulty breathing. Some mild cases in
victims of COVID-9 infection can heal.
However, several other severe cases resulted
in shortness of breath and lung damage which
leading to death.
Currently, 213 countries, including
Indonesia, are affected by disease outbreaks,
namely the COVID-19 virus and by WHO it
has been designated as a pandemic or disease
outbreak that can spread to various regions.
At least from December 2019, when the
COVID-19 case was announced in China,
until April 11, 2020, 1,569,504 people were
confirmed positive for COVID-19, with a
total of 95,269 deaths worldwide due to
COVID. In Indonesia, it was found that
people affected by COVID were found
around March 2, 2020, and until April 11,
2020, 3842 people were confirmed positive
for COVID-19, with a death rate of 327
people. The number of cases of the Corona
COVID-19 virus in Indonesia increased by
10,994 on Monday (February, 1, 2021). The
total positive became 1,089,308, recovered
883,682, and died 30,227 cases.The number
of suspects monitored today is 76,343 people.
While there are 175,349 active cases.
The public is urged to take three
important steps to fight the fast spread of
COVID-19. The three steps are reducing the
risk of being exposed to COVID-19, finding
correct information regarding COVID-19,
and what needs to be done can get sick. Also,
wash your hands for at least 20 seconds, use
International Journal of Environmental Engineering and Development
DOI: 10.37394/232033.2023.1.10
Waljiyanto, M. Al Musadieq,
Edy Yulianto, Yusri Abdillah
E-ISSN: 2945-1159
84
Volume 1, 2023
hand sanitizer (at least 60% alcohol) if soap
and running water are not available, keep a
distance of at least one meter.
The energy sector is one of the sectors
that plays an important role in economic
activity and national security. Energy
processing which also includes the use,
exploitation and supply of energy should be
carried out in a sustainable manner. In the
long term, management in the energy sector
requires planning with integrity in the
development of resources used to provide
energy in the long term.
The industrial sector is a vital sector in
economic development and growth in
Indonesia. The industrial sector is also a
dominating energy user. Apart from that,
another sector that also requires a lot of
energy to support the movement of the
economy is transportation, where the
industrial sector also has needs in the
transportation sector.
PT Pertamina is a state-owned company
that carries out oil and gas business activities
in the Upstream to Downstream Sectors. This
business entity has the main mission as a
producer of oil and gas, as well as developing
new and renewable energy, processing and
distributing all fuel oil and gas needs in
Indonesia since December 10, 1957. This
company supports the government's efforts in
realizing national energy security and always
develops into world-class national energy
company.
In PT Pertamina's Corporate Marketing
Business (CMB), there are six primary
business unit sizes, namely Industrial Fuel,
Aviation, Petrochemical, Gas Business,
Lubricants, and Patra Niaga. Of the six
business unit sizes, three business units
dominate the CMB volume, namely
Industrial Petroleum, Aviation and
Petrochemical Products. This is supported by
predictive data for revenue growth and sales
volume for 2020-2026, showing that 77.8%
of the CMB business units (Industrial Fuel,
Aviation and Petrochemical Products)
dominate PT Pertamina's revenue.
Obstruction of economic activity
automatically causes business actors to make
efficiency to reduce losses. As a result, many
workers are laid off or even laid off (layoffs).
The rate of labor absorption will not be as
large as the number of workers who have
been laid off. The difference in workers who
are not absorbed will then fall into the
unemployment group.
The government is preparing several
scenarios to deal with COVID-19. According
to the Minister of Finance, the existence of
COVID-19 will result in a decline in
economic growth in Indonesia, reaching a
negative 0.4 per cent by the end of 2020. The
COVID-19 outbreak, which has become a
pandemic, will have an impact on the most
vulnerable corporate sectors, namely
manufacturing, trading, transportation and
accommodation companies. The existence of
COVID-19 will result in disruption of
activities that have an impact on business
performance and decrease demand for a
company's products. The impact of the
COVID-19 was that the price of crude oil in
Indonesia fell to USD 31 per barrel.
Furthermore, the existence of the
coronavirus will have an impact on the
transportation sector regarding the reduction
in the price of aviation fuel for airlines.
Besides, it also has an impact on decreasing
the use of fuel oil (BBM) by the community.
The fuel produced by PT Pertamina includes
Solar Oil (High-Speed Diesel), Diesel Oil
(Industrial / Marine Diesel Oil), and Fuel Oil
(Industrial / Marine Fuel Oil). Thus, PT
Pertamina must anticipate a decrease in the
volume of demand.
The first period of research (April-June
2020) estimated the demand for
petrochemical demand throughout 2020. The
second period of research (July-September
2020) projections and reprojections were
performed by adding fundamental macro
aspects, both currently occurring, as well as
examples. Two economic crises in 1998 and
2008 as a comparison, then in this third part
(October-December 2020), a post-COVID-19
Action Plan is carried out.
After the pandemic period ends
(hopefully it ends sooner), a more detailed
identification is needed, given the minimum
International Journal of Environmental Engineering and Development
DOI: 10.37394/232033.2023.1.10
Waljiyanto, M. Al Musadieq,
Edy Yulianto, Yusri Abdillah
E-ISSN: 2945-1159
85
Volume 1, 2023
six months of recovery to return to its original
position. Planning is the initial preparation
for action. At least analytically, planning
should be separated from implementation so
that critical policy decisions can be taken and
implications can be understood in advance of
action.
In the Indonesian context, many
lessons can be taken by stakeholders,
particularly companies, regarding the disaster
management efforts that have been carried
out so far. When it is related to the disaster
management cycle, most companies in
Indonesia are still engaged in emergency
response efforts, and very few are involved in
prevention and mitigation, disaster risk
reduction, and restoration of livelihoods after
a disaster. So it is natural that when there is
no disaster, we seldom hear about the work of
companies in the disaster sector. Therefore,
the aim of this research is to forecast demand
for petrochemicals in 2021 and 2022, after the
end of Covid-19. And this is the novelty of
research that occurs as a result of the impact of
a global disaster that affects all sectors
worldwide, including companies. And at the
same time provide literature to predict a
changing sector affected by a global pandemic.
2. Literature Review
2.1. Petrochemical
Petrochemicals are any chemical fuels
that are obtained from fossil fuels.
Petrochemicals include purified fossil fuels
such as methane, propane, butane, gasoline,
kerosene, diesel fuel, aircraft fuel, pesticides,
herbicides, fertilizers, plastics, asphalt, and
human-made fibres. There are several types of
petrochemicals produced by Pertamina,
including Polytam, Propylene, Benzene,
Paraxylene, Asphalt, Sulfur, Low Aromatic
White Spirit (LAWS), Special Boiling Point
(SBP-XX), Subang Condensate, Pertasol,
Minarex, Paraffinic Oil, Green Coke, Slack
Wax, Tenac Sticker, TB 192, Sophy, and
Smooth Fluid-05.
Petrochemical products produced by
Pertamina are sold to consumers of
petrochemical products which consist of
agencies, end-users, and trading companies.
The sale of petrochemical products is carried
out on a FOB basis, in which the agent or
consumer takes the product he wants. However,
in line with market dynamics, petrochemicals
have been selling on a CFR basis. There are
several sales mechanisms for petrochemical
products, including:
1) Through Agency
2) Agencies usually provide varying
discounts based on the policies of each
product and competitor prices.
3) Selling Directly to End-Users
4) Through a tender (auction)
5) Through natural selection (beauty
contest).
The payment systems applied by
Pertamina when trading Petrochemicals
include cash and credit. Cash Before Delivery
for most Petrochemical products and Auto
collection are applied for cash payments.
Meanwhile, for credit payments, it can be
guaranteed by an LC / SKBDN / Bank
Guarantee, or it can be without a guarantee,
namely using a TT which is intended for a
subsidiary.
2.2. Vector Autoregressive (VAR)
The Vector Autoregressive (VAR) model
is an extension of the Autoregressive (AR (p))
model. Suppose the Autoregressive (AR (p))
model is one of the univariate time series
analysis models. In that case, the Vector
Autoregressive (VAR) model is one of the
multivariate time series analysis models (Wei,
2006). According to Gujarati (2003), VAR is a
method similar to a system of simultaneous
equations which considers several endogenous
variables together. The VAR model is used
when there is a two-way causality relationship
between endogenous variables (Cryers, 2008).
The equation for the VAR model with the order
p can be seen in the following equation:
= t-period endogenous variable vector
of size m × 1
International Journal of Environmental Engineering and Development
DOI: 10.37394/232033.2023.1.10
Waljiyanto, M. Al Musadieq,
Edy Yulianto, Yusri Abdillah
E-ISSN: 2945-1159
86
Volume 1, 2023
= coefficient matrix of endogenous
variables measuring m × m
= vector of endogenous variables at
time lag to ( )
size m × 1
= remaining vector of size m × 1
= length of lag
m = many endogenous variables
In the VAR model, each endogenous
variable is described by the value of the
endogenous variable in the past and the value
of other endogenous variables in the past and
the present. The VAR method explains that
each variable contained in the model depends
on the past movements of the variable itself and
the past movements of other variables
contained in the system of equations. The VAR
method can be used to project a system of time
series variables and analyze the dynamic
impact of the disturbances contained in the
equation.
2.3. Response Impulse Method
Impulse Response Function (IRF) is used to
detect the current and future response of each
variable due to a change or shock of a particular
variable (Gujarati, 1988). IRF aims to
determine how shock affects the economy. IRF
describes how the rate of the shock of a variable
against other variables so that through this IRF,
it can be seen the length of the effect of a
shock/shock of a variable on other variables
(Greene, 2003).
3. Research Methodology
This study was a quantitative research with
the exploratory and descriptive approach.
Exploratory research is a research that aims to
explore (excavate) information (scientific) (.
(Sumardi & Adji Achmad Rinaldo, 2018;
Fernandes & Solimun, 2017; Hakim &
Fernandes, 2017). While descriptive research is
research that aims to describe (describe clearly
and in detail) the relevant aspects of the
phenomena that are of interest to researchers
(Solimun & Fernandes, 2017; Fernandes et al.,
2014; Purbawangsa et al., 2020). The
exploratory and descriptive research does not
use hypotheses in its implementation.
Exploratory and descriptive approaches are
used to solve problems that exist in the demand
system of PT Pertamina, which is affected by
COVID-19. The location of this research is at
PT Pertamina. The time for phase 3 research is
carried out from October to December 2020.
The variables used in this study are
Petrochemical Demand as the dependent
variable (Y1). The data used are monthly
secondary data with a period from January
2016 to September 2020. In this study, the
VAR forecasting method and impulse response
function were used in optimally measuring the
level of demand for petrochemical products at
PT Pertamina.
VAR (Vector Autoregressive) is a
multivariate forecasting model used to build a
forecasting system from interrelated time series
data and to analyze the dynamic effects of
random factors that disrupt the system.Vector
Auto Regression (VAR) is usually used to
project a system of time series variables and to
analyze the dynamic impact of the disturbance
factors contained in the variable system.
Basically, VAR analysis can be matched with a
simultaneous equation model, because in VAR
analysis, several endogenous variables are
considered in a model.
The advantages of VAR analysis include:
(1) This method is simple, there is no need to
worry about distinguishing which variables are
endogenous from which variables are
exogenous; (2) The estimation is simple, where
the ordinary OLS method can be applied to
each equation separately; (3) The forecast
results obtained using this method are in many
cases better than the results obtained using even
complex simultaneous equation models. Also,
VAR Analysis is a very useful analysis tool,
both in understanding the interrelationship
between economic variables and in the
formation of structured economic models.
VAR analysis can be used to predict products
due to many factors that affect the forecasting
level of Pertamina's product marketing.
The forecasting method is used to predict
the product demand value until the end of 2020
to get the best policy for PT Pertamina as well
as the Impulse Response Function will be used
International Journal of Environmental Engineering and Development
DOI: 10.37394/232033.2023.1.10
Waljiyanto, M. Al Musadieq,
Edy Yulianto, Yusri Abdillah
E-ISSN: 2945-1159
87
Volume 1, 2023
in forecasting analysis. The response impulse is
used to see how the demand reaction of the
Petrochemicals products, when other variables
get a shock in the current conditions, namely
the COVID-19 outbreak.
4. Result and Discussion
4.1 Stationary to Average
There are two kinds of static properties;
stationarity to variety and stationarity to the
average. So, it is necessary to test stationarity
against the average. The stationarity test
against the mean can be done by using the fuller
augmented dickey test as follows.
Hypothesis:
H0: There is a unit root (data is not stationary)
H1: There is no unit root (stationary data)
Decision: Reject H0 if p-value <α (0.01)
The results of the Stationarity Test can be seen
in the following table.
Table 4. 1 Stationarity Test
Variabel
Augmented Dickey-Fuller
Decicsion
P-value
With constant
P-value
With Constant
and Trend
Petrochemical
Aromatic & Olefin
0,005379
0,1282
Stationary
Bitumen
0,007041
0,1456
Stationary
Special Chemical
7,744e-006
7,568e-005
Stationary
Overall Petrochemical
0,0001
0,001053
Stationary
Source: Secondary data processed (2020)
From the stationarity test, it can be seen
that all variables produce stationary test results
where the variables are Aromatic & Olefin,
Bitumen, Special Chemical, and Overall
Petrochemical are stationer.
4.2. Determination of the Optimum Lag
After testing the stationarity, then the
optimal lag length is measured. Determination
of the Optimum Lag is carried out using the
help of GRETL software. The results obtained
for demand products are as follows.
Table 4.2 Determination of the Optimum Lag
No.
Type of Petrochemical Product
Optimum Lag
1.
Aromatic & Olefin
2
2.
Bitumen
5
3.
Special Chemical
3
Source: Secondary data processed (2020)
So that information is obtained that
each product has a different lag because each
product has different data characteristics.
Determination of the Optimum Lag based on
actual conditions and existing data. The
optimum lag is used for Vector Autoregressive
(VAR) analysis.
4.3. VAR Forecasting Model
Shaped models are models that are estimated
using the least-squares method. The following
equation is obtained.
International Journal of Environmental Engineering and Development
DOI: 10.37394/232033.2023.1.10
Waljiyanto, M. Al Musadieq,
Edy Yulianto, Yusri Abdillah
E-ISSN: 2945-1159
88
Volume 1, 2023
t-i = Demand Bitumen in period t-
i; i=1,2,3
AOt-i = Demand Aromatic in period t-
i; i=1,2,3
SCt-i = Demand Special Chemical in
period t-i; i=1,2,3
4.4. Forecasting Results
The data that will be predicted are as many
as 15 periods from October 2020 to December
2021.
Table 4.3 Results of Petrochemical Products Forecasting
Time
Demand (MTD in Thousand KL)
Aromatic & Olefin
Bitumen
Special Chemical
Oct 2020
27631
26774
581090
Nov 2020
33410
22289
694830
Dec 2020
35119
22825
946620
Jan 2021
29457
46572
280597
Feb 2021
36754
49176
207571
Mar 2021
50252
54857
418137
Apr 2021
45879
59136
362976
May 2021
46144
60089
336813
International Journal of Environmental Engineering and Development
DOI: 10.37394/232033.2023.1.10
Waljiyanto, M. Al Musadieq,
Edy Yulianto, Yusri Abdillah
E-ISSN: 2945-1159
89
Volume 1, 2023
Time
Demand (MTD in Thousand KL)
Aromatic & Olefin
Bitumen
Special Chemical
June 2021
49408
79831
525070
July 2021
56680
83223
483684
August 2021
57491
79095
798397
Sept 2021
67221
75985
1038154
Oct 2021
69868
78993
493975
Nov 2021
73800
85713
490345
Dec 2021
78088
92344
495597
Source: Secondary data processed (2020)
Based on the forecasting results above,
information can be obtained that:
1) Special Chemical products are
predicted to fluctuate from month to
month.
2) Bitumen products are predicted to
increase from month to month even
though the increase is not very visible.
3) Aromatic & Olefin products are
predicted to increase from month to
month although the increase is not very
visible.
4.5. PT. Pertamina Product Demand Risk
Mitigation
Based on the results of forecasting the
demand for PT Pertamina’s products under
normal conditions with assumptions if COVID-
19 Pandemic ends in December 2021.
Table 4.4. Results of Product Risk
Mitigation of PT. Pertamina
Variable
Forecasting
Demand
Petrochemical
Aromatic
45%
Bitumen
45%
Special Chemical
41%
Source:
Secondary data
processed (2020)
Based on table above, the impact of risk
caused by COVID-19 in Petrochemical is
predicted to be more significant is the Aromatic
and Bitumen product. The effect of COVID-19
in reducing the economy causes the industry to
reduce the amount of production. This
explanation is in contrast to diesel users who
are dominated by large industries that have
sufficient capital to anticipate a recession from
COVID-19. This shows as a whole that the
longer the pandemic occurs in Indonesia, the
more impact it will have on PT Pertamina,
especially Pertamina’s products. COVID-19
has an impact on the Petrochemical sector,
Pertamina can increase sales of products that
are affected by low risk, namely Special
Chemical, by expanding its domestic market
share.
5. Conclusion and Recomendation
Based on the results of the analysis, the
results of the analysis prediction shows that the
demand for petrochemicals products of PT
Pertamina will increase starting in 2021. It is
assumed that the Petrochemical product that
has a low risk is Special Chemical. On the other
hand, one petrochemical product product that
has a high risk of COVID-19 is the Aromatic.
The suggestions obtained from this research are
as follows: PT Pertamina CMB needs to
prepare adaptive policies by taking into account
several different scenarios by conducting
evaluation and reprojection of Petrochemical in
Responding to the Impact of Covid-19.
References
[1]. Cryer, J. D., & Chan, KS. 2008. Time
Series Analysis: With Application in R:
International Journal of Environmental Engineering and Development
DOI: 10.37394/232033.2023.1.10
Waljiyanto, M. Al Musadieq,
Edy Yulianto, Yusri Abdillah
E-ISSN: 2945-1159
90
Volume 1, 2023
Second Edition. USA: Springer Science
dan Business Media, LLC.
[2]. Dielman, T. E. 2009. Email: A Note on
Hypothesis Tests after Correction for
Autocorrelation: Solace for the Cochrane-
Orcutt Method?. Journal of Modern
Applied Statistical Methods, 8(1), 9.
[3]. Fernandes, A.A.R. and Solimun (2017).
Moderating effects orientation and
innovation strategy on the effect of
uncertainty on the performance of business
environment. International Journal of Law
and Management, Vol. 59 No. 6, pp. 1211-
1219. https://doi.org/10.1108/IJLMA-10-
2016-0088
[4]. Fernandes, A.A.R., I Nyoman Budiantara,
Bambang Widjanarko Otok, Suhartono.
(2014). Reproducing kernel Hilbert space
for penalized regression multi-predictors:
case in longitudinal data. International
Journal of Mathematical Analysis, Vol. 8,
2014, no. 40, 1951-1961.
http://dx.doi.org/10.12988/ijma.2014.4721
2
[5]. Greene, W. H. 2003. Econometric analysis.
Pearson Education India.
[6]. Gujarati, D. 1988. Ekonometrika Dasar
XVII. Jakarta: Erlangga.
[7]. Gujarati, D. 2003. Basic Econometrics.
Forth Edition. Singapura: McGraw-Hill.
[8]. Hakim, W. and Fernandes, A. (2017).
Moderation effect of organizational
citizenship behavior on the performance of
lecturers. Journal of Organizational Change
Management, Vol. 30 No. 7, pp. 1136-
1148. https://doi.org/10.1108/JOCM-11-
2016-0242
[9]. PaskaSugeti, A. E., Supaya, S., & Suratno,
A. 2019. Pengaruh Harga Produk Dan Kurs
Terhadap Volume Ekspor Produk Man
Polo Shirt Di Pt Apparel One
Indonesia. JOBS (Jurnal Of Business
Studies), 3(2), 173-184.
[10]. Purbawangsa, I.B.A., Solimun, S.,
Fernandes, A.A.R. and Mangesti Rahayu,
S. (2020). Corporate governance, corporate
profitability toward corporate social
responsibility disclosure and corporate
value (comparative study in Indonesia,
China and India stock exchange in 2013-
2016). Social Responsibility Journal, Vol.
16 No. 7, pp. 983-999.
https://doi.org/10.1108/SRJ-08-2017-0160
[11]. Solimun., and Fernandes, A.A.R.
(2017). Investigation the mediating
variable: What is necessary? (case study in
management research). International
Journal of Law and Management, Vol. 59
No. 6, pp. 1059-1067.
https://doi.org/10.1108/IJLMA-09-2016-
0077
[12]. Sumardi. and Adji Achmad Rinaldo,
A.A.R. (2018). The mediating effect of
service quality and organizational
commitment on the effect of management
process alignment on higher education
performance in Makassar, Indonesia.
Journal of Organizational Change
Management, Vol. 31 No. 2, pp. 410-425.
https://doi.org/10.1108/JOCM-11-2016-
0247
[13]. Wei, W. W. 2006. Time series analysis.
In The Oxford Handbook of Quantitative
Methods in Psychology: Vol. 2.
Contribution of Individual Authors to the
Creation of a Scientific Article (Ghostwriting
Policy)
The authors equally contributed in the present
research, at all stages from the formulation of the
problem to the final findings and solution.
Sources of Funding for Research Presented in a
Scientific Article or Scientific Article Itself
No funding was received for conducting this study.
Conflict of Interest
The authors have no conflicts of interest to declare
that are relevant to the content of this article.
Creative Commons Attribution License 4.0
(Attribution 4.0 International, CC BY 4.0)
This article is published under the terms of the
Creative Commons Attribution License 4.0
https://creativecommons.org/licenses/by/4.0/deed.en
_US
International Journal of Environmental Engineering and Development
DOI: 10.37394/232033.2023.1.10
Waljiyanto, M. Al Musadieq,
Edy Yulianto, Yusri Abdillah
E-ISSN: 2945-1159
91
Volume 1, 2023
