2014). This combination of machine and manual
methods often takes a long time to develop and it's
error-prone.
A more convenient way is to call auto_ARIMA
directly. It turns out that when the values of the
parameters are (0, 1, 1), the AIC value equals
5014.207, which is the smallest value in all the test
models. When comparing the AIC of several models
for a given data set, the "best" model among all those
available for the data set is the one with the lowest
AIC score. Even if only subpar models are taken into
account, the AIC will still be able to choose the best
one. As a consequence, the ARIMA (0, 1, 1) is the best
algorithm for this collection of data (Mazerolle 2006
& Gasper and Mbwambo 2023).
3.4 The Comparison Between Actual
Values and Predicted Values
Figure 5 and Table III show the actual values of the
weekly data set and predicted values of the ARIMA
(0, 1, 1) model. As it is shown in the plot and table,
the Urals oil’s price will rise next week.
Figure 5: Plot of comparison with real and anticipated
values (Photo/Picture credit: Original).
4 CONCLUSIONS
The price of Urals oil is not stationary and it can be
affected by several factors, such as oil commodity and
financial attributes, supply and demand in the oil
market, the international economic situation,
fluctuations in the US dollar's exchange rate, and the
role of the law of value on the five major factors
affecting it. According to the study’s findings, the
Autoregressive Integrated Moving Average Model
(ARIMA) (0, 1, 1) is the best model used for the
future value prediction of the oil and it presented that
the average price in the next week will increase.
The study of oil price trends and the development
and application of forecasting models are both
important tools for financial strategy development
and important macroeconomic management tools.
However, at the same time, various models also have
certain limitations and risks, which need to be flexibly
selected in light of the specific market environment
and needs.
Besides, this model can also be used to conjecture
the price of another object in the future. The
seasonality of the data can also be taken into account
when constructing the model. BIC can be introduced
in addition to AIC to help provide a more
comprehensive view.
REFERENCES
G. Marbuah, Understanding crude oil import demand
behaviour in Africa: The Ghana case. Journal of
African Trade, vol.4, no.1-2, 2017, pp. 75-87.
D. J. Shaw, J. D. Oldfield, Landscape science: a Russian
geographical tradition. Annals of the association of
american geographers, vol.97, no.1, 2007, pp. 111-
126.
G. Ibendahl, The Russia-Ukraine conflict and the effect on
fertilizer. Department of Agricultural Economics,
Kansas State University: Manhattan, KS, USA. 2022.
M. Nerlinger, and S. Utz, The impact of the Russia-Ukraine
conflict on energy firms: A capital market perspective,
vol.50, 2022, pp.103243.
V. J. P. D Martinho, Impacts of the COVID-19 pandemic
and the Russia–Ukraine conflict on land use across
the world. Land, vol.11, no.10, 2022, pp.1614.
A. Razek, N. H. Galvani, V. et al. Can US Strategic
Petroleum Reserves Calm a Tight Market
Exacerbated by the Russia-Ukraine Conflict? 2023,
pp.4441644.
L. T. Ha, Dynamic interlinkages between the crude oil and
gold and stock during Russia-Ukraine War: evidence
from an extended TVP-VAR analysis. Environmental
Science and Pollution Research, vol.30, no.9, 2023,
pp. 23110-23123.
A. Ariyo, A. Adewumi, et al. Stock price prediction using
the ARIMA model. In 2014 UKSim-AMSS 16th
international conference on computer modelling and
simulation, IEEE. 2014, pp. 106-112.
Contreras, J., Espinola, R., et al. ARIMA models to predict
next-day electricity prices. IEEE transactions on
power systems, 2003, 18(3), pp. 1014-1020.
R. A. Ahmed, A. B. Shabri, Daily crude oil price forecasting
model using arima, generalized autoregressive
conditional heteroscedastic and support vector
machines. American Journal of Applied Sciences,
vol.11, no.3, 2014, pp. 425.
M. Mazerolle, Improving data analysis in herpetology:
using Akaike's Information Criterion (AIC) to assess
the strength of biological hypotheses. Amphibia-
Reptilia, vol.27, no.2, 2006, pp. 169-180.
L. Gasper, H. Mbwambo, Forecasting crude oil prices by
using ARIMA model: evidence from Tanzania. 2023.