Can AI Predict the Oil Price?

Artificial Intelligence (AI) can do many things, but can it predict the oil price?

The answer to that question is no, according to Alex Stevens, the Manager of Policy and Communications at the Institute for Energy Research (IER), which describes itself as a not for profit organization that conducts intensive research and analysis on the functions, operations, and government regulation of global energy markets.

“AI will bring a lot of benefits to the oil and gas industry, but people who believe it has some sort of predictive power over market prices are greatly overstating what AI is capable of doing,” Stevens told Rigzone.

Answering the same question, Hussein Shel - the Director, Chief Technologist, and Head of Upstream for Energy and Utilities at Amazon Web Services (AWS) – said, “machine learning and artificial intelligence technologies, including generative AI and similar language models, are not specifically designed for predicting financial markets, including oil prices”.

“While these models can process and generate text based on the input they receive, predicting complex and volatile financial market movements like oil prices requires a deep understanding of economic, geopolitical, and industry-specific factors,” Shel told Rigzone.

“Oil prices are influenced by a wide range of variables, such as supply and demand dynamics, geopolitical events, economic indicators, technological advancements, etc. Predicting oil prices accurately often involves complex quantitative models, data analysis, and energy markets expertise,” Shel added.

“Additionally, the assistance provided by these models is based on the data they’ve been trained on, and they may not have access to the most current or specialized information. As such, AWS believes that these models could be used to provide a good starting point for research and understanding,” Shel continued.

Offering a few examples, Shel highlighted “information synthesis”, adding that “AI models can analyze and synthesize large amounts of text from diverse sources, helping to provide users with a comprehensive view of a particular topic”.

Shel also flagged “contextual understanding”, stating that “AI models can be used to analyze the context of a question or topic and provide explanations in a way that’s easy to understand” and “trend identification”, adding that “by analyzing patterns and recurring themes in the provided data, these models can help identify trends”.

When Al Salazar, the Senior Vice President at Enverus Intelligence Research (EIR) was asked if AI can predict the oil price, the EIR representative told Rigzone that “AI could have some advantages in terms of data and computing power that conventional forecasters don’t” but added that “one thing that AI could struggle with is correctly timing OPEC actions along with geopolitical driven-supply outages”.

“AI could offer both the supply and demand side of commodity markets some efficiency gains,” Salazar said.

“However, it’s likely too soon to say how impactful it will be,” Salazar added.

At the time of writing, the price of Brent crude oil is trading at $88.57 per barrel and the price of WTI Crude is trading at $85.58 per barrel. Brent closed at $83.36 per barrel on August 24 before rising to a close of $88.55 per barrel on September 1, while WTI closed at $79.95 per barrel on August 24 before increasing to a close of $85.55 per barrel on September 1.

In its latest short term energy outlook (STEO), which was released last month, the U.S. Energy Information Administration (EIA) projected that the Brent spot price will average $82.62 per barrel this year and $86.48 per barrel next year. The EIA’s August STEO sees the WTI spot price averaging $77.79 per barrel in 2023 and $81.48 per barrel in 2024.

In a report sent to Rigzone last week, Standard Chartered predicted that the ICE Brent price would average $91 per barrel this year and $98 per barrel next year. That report projected that the NYMEX WTI price would come in at $88 per barrel in 2023 and $95 per barrel in 2024.

To contact the author, email andreas.exarheas@rigzone.com