Research demonstrates evolutionary algorithm could be used to predict oil price rises

March 1, 2016 by Alan Williams

Future fluctuations in oil prices could be forecast using a combination of previous statistics and complex computer algorithms, according to new research.

Academics from the Gulf University for Science and Technology and Plymouth University used a range of programmed models to accurately predict previous rises and falls in the commodity's value over a period from January 1986 to June 2012.

They discovered that when provided with several years of data, a gene expression programming (GEP) model almost perfectly predicted subsequent years' figures, outperforming traditional statistical techniques.

It is also more accurate than other (NN) models, and the widely-used autoregressive integrated moving average (ARIMA) system.

Crude oil holds an important and growing role in the world economy, with past studies demonstrating a close relationship between oil price and the GDP growth rate.

Yet oil price prediction has always proved to be an intractable task due to the intrinsic complexity of oil market mechanisms, and other outside influences such as weather, stock levels, political aspects and even people's psychological expectations.

Dr Ahmed El-Masry, Associate Professor in Financial Management at Plymouth University, said:

"The price of affects people everywhere, whether they live in countries that are net importers or exporters of the commodity. And the fluctuations of recent times have led to great economic uncertainty and that will only continue as consumption – and therefore demand – increased. If policy makers and economists had a tool which could accurately predict future prices, it would enable them to plan for the future at the same time allowing consumers to have an idea of the rising or falling costs they might incur."

GEP is one of the most recent developments in the field of artificial evolutionary systems, but has previously been shown to accurately forecast exchange rates, short-term electricity load and even daily evaporation in Turkish lakes.

It works through a complex tree structure that learns and adapts by changing its size, shape, and composition, much like a living organism. It also benefits from a simple genome to keep and transmit the genetic information and a complex phenotype to explore the environment and adapt to it.

Explore further: Supply and demand based oil price shocks have different effect on the macroeconomy

More information: Mohamed M. Mostafa et al. Oil price forecasting using gene expression programming and artificial neural networks, Economic Modelling (2016). DOI: 10.1016/j.econmod.2015.12.014

Related Stories

Lifting crude oil ban means lower gasoline prices

December 21, 2015

Lifting the ban on crude oil exports will reduce gasoline prices in the United States, according to an analysis co-written by Charles Mason, the H.A. True Chair in Petroleum and Natural Gas Economics at the University of ...

Benefits by the barrel

April 11, 2011

(PhysOrg.com) -- Countries rich in oil have long been associated with the "resource-curse paradox" - a principle which states they will suffer, rather than benefit, in the long run. Not so, new research by a Cambridge Gates ...

Why we will still need oil and gas in the future

February 29, 2016

Worldwide, total oil demand keeps growing. Low prices are fueling this trend. To remain competitive, oil companies need to reduce their production costs. Siemens is supporting their efforts with a comprehensive portfolio ...

Recommended for you

Evaluation of scientific rigor in animal research

December 2, 2016

The "reproducibility crisis" in biomedical research has led to questions about the scientific rigor in animal research, and thus the ethical justification of animal experiments. In research publishing in the Open Access journals ...

Computer learns to recognize sounds by watching video

December 1, 2016

In recent years, computers have gotten remarkably good at recognizing speech and images: Think of the dictation software on most cellphones, or the algorithms that automatically identify people in photos posted to Facebook.

5 comments

Adjust slider to filter visible comments by rank

Display comments: newest first

gkam
1 / 5 (4) Mar 01, 2016
Prediction is necessary for corporate planning, but the "O'l Bidness" has already ruined itself with greed and and selfishness.

We are going elsewhere for energy, and finding it to be better, cleaner, and eventually less expensive. We love our electric vehicle, and the fact it runs on sunshine, collected from our roof. We save more money on the vehicle than we do for the house power.
Rosser
5 / 5 (4) Mar 01, 2016
My aunt, who was an economist for Gulf Oil, once told me that "statistics don't lie, but statisticians do." Just about anyone can take existing data and fit it to a curve. What concerns me about this model is the fact that the underlying drivers of oil prices have changed over the years, and will continue to evolve in the future. It used to be supply and demand. Now it's supply, demand, war, politics, alternative energy sources, and perhaps most importantly, perceptions. Economists and the aforementioned suppliers and demanders try to outguess the environment in which they operate and, as often as not, psych themselves out. This is what has, and will continue to, lead to the wildly fluctuating prices we have experienced, even though old fashion supply and demand really hasn't changed very much. I wish them well with their model, but I won't take it to the bank.
gkam
1 / 5 (4) Mar 01, 2016
The yo-yoing of prices has many organizations looking at alternatives. Big Oil has become a victim of its own greed.
Whydening Gyre
5 / 5 (2) Mar 01, 2016
G,
You speak of "Big Oil" as if it has it's own persona.
That "persona" is nothing more than a collection of HUMANS.
gkam
1 / 5 (2) Mar 01, 2016
Yes, just like Boy Scouts, terrorists, churchgoers, and the KKK.

But how do they act overall?

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.