Olive oil prices globally have surged to unprecedented levels due to poor harvests caused by drought and high spring temperatures in major producing countries, notably Spain.

Although prices at origin have decreased from their peak in mid-January, retail prices remain elevated, leading to changes in consumer behavior in traditionally high olive oil-consuming regions.

Industry experts expect prices to fall as global olive oil production is anticipated to reach approximately three million tons in the 2024/25 crop year. However, the future price trajectory remains uncertain.

In response, a researcher from Andalusia, Spain's largest olive oil-producing region, has developed an artificial intelligence (AI) program to forecast olive oil prices.

Diego Hueltes, a computer engineer and CEO of TADA.ai, created three predictive models: a one-week forecast, a four-week forecast, and a model to predict price direction.

"I come from Alcalá la Real, a town in Jaén where olive farming is a major livelihood, and there's a strong culture around olive oil," he told Olive Oil Times.

"I was intrigued by how the elders could predict market movements based on weather and prices," he added. "If they could do it through experience, my hypothesis was that an AI model could achieve the same more systematically."

Hueltes employed machine learning algorithms and AI research to analyze historical olive oil prices, meteorological data, and production figures, providing accurate price estimates for 2017 and 2018.

"I developed two models," Hueltes explained. "The first predicted the price as an absolute number. For example, if the model forecasts a price of €10.00 next week, the actual price would likely be between €9.97 and €10.03 with a mean error of three percent."

"The second model predicted whether the price would go up or down the following week, and it accurately forecasted price direction 76 percent of the time," he added. "To evaluate this model, I used a financial technique analyzing returns. If I had invested €100 following the model's advice between 2017 and 2018, I would have €140 after a year."

Since 2018, various factors such as U.S. tariffs on Spanish olive oil, the COVID-19 pandemic, the Russian invasion of Ukraine, and Europe's historic drought have occurred.

"Although the model's scientific basis remains valid, it wouldn't be applicable for 2024," Hueltes said. He has made his research available on GitHub for public access.

"I'm a strong proponent of open source, and I believe scientific research, especially in AI, should be universally accessible and free," he said. "Since there was little open and accessible work in olive oil, I chose to make all my research public."

Hueltes hopes this technology will benefit the world's largest olive oil-producing region in the future.

"The AI model, using price, production, and meteorological data, can identify patterns in the data that are challenging for humans, even experts, to detect," he said. "These patterns are entirely feasible for AI models."

According to Hueltes, predicting olive oil prices "allows for the optimization of the oil trade, particularly for small producers, as they receive indicators on whether prices are fair or if they should wait or act quickly."

Furthermore, the research could benefit various stakeholders across the olive oil value chain, including farmers, retailers, distributors, consumers, investors, and traders.

Farmers and producers can plan their sales strategies more effectively to maximize profits and manage resources efficiently.

Retailers and distributors can use accurate price predictions to manage inventory and develop competitive pricing strategies.

Consumers can make informed purchasing decisions based on potential price fluctuations, such as buying in bulk when prices are expected to rise.

Finally, investors and commodity traders can make better investment decisions and increase their returns. Understanding price trends can also help formulate policies to support the agricultural sector and stabilize the market.

While Hueltes noted that the research may not directly address climate change, which has contributed to recent production declines, "it can help understand how climate factors affect olive oil production."

"The open-source nature of the research enables the development of new models to make the olive oil trade more equitable," he added.