By Benoit Bellone, Head of Research and Senior Research Data Scientist, QuantCube Technology

As futures and options traders seek to harness the full potential of data, AI-powered tools are quickly becoming the focus. The advent of large-language models (LLMs) like ChatGPT have fired the imagination and renewed conversations around the art of the possible, but, as with many evolving technologies, there are misconceptions that exist around how AI can and should be applied.

For many business use cases, AI tools can deliver immediate value that can be used to improve services and internal processes, often through the automation of complex tasks. Once set up, these automation tools will require only rudimentary intervention and refinement from data scientists. In other use cases, however, the outputs of AI-powered tools, such as machine learning models, cannot be operationalised on their own. This would be entirely irresponsible and would leave users exposed to many of the real problems that are inherent in AI-powered technologies, such as erroneous outputs or ‘hallucinations’.

One area that’s gaining increased attention – and where human oversight is focused on ensuring the power of AI and data analytics is optimised – is the mining of huge quantities of alternative data to deliver real-time macroeconomic insights. Such insights, for example with regard to commodities, can give human decision-makers a critical edge in their trading strategies, enabling them to spot trends and identify market turning points ahead of their peers, helping to maximise performance.

Gaining actionable insights from alternative data fast enough to make a difference in trading strategy requires advanced AI technology, computing power and robust data science expertise. This is where tools such as Natural language processing (NLP) models come into their own, enhancing data scientists’ ability to treat information, to extract and classify data, and to create real time indicators or nowcasts. This is a secure application of AI, as each use case has humans as the arbiters of what is true and useful in a closed data universe—the universe being constructed from data streams that have been carefully curated for a specific job.

In contrast, models that deliver outputs that cannot be verified, i.e. black box solutions, are of no use in the context of commodities trading, as investors need precision and explainable methodologies behind the models that inform the decisions they make.

A fundamental approach

The real value of machine learning and deep learning models for the analysis of macroeconomic indicators and commodity trading is their ability to handle vast amounts of unstructured data, such as satellite data or textual data. Salient information, for example regarding weather patterns, can be extracted from alternative data sources, which data scientists can then correlate with official data to ensure the methodology behind their construction is sound. Once this is confirmed, through comparison against official statistics over time, the indicators can provide invaluable insights ahead of the publication of official data.

For every use case, the fundamentals of economic analysis must take precedence. If the supply of a commodity is suppressed, for example, its price will typically rise; and if one of the world’s largest exporters of wheat is invaded and thrust into war, as was the case with Ukraine, the price of wheat will initially climb rapidly. When a market shock like this occurs, however, real-time insights into the knock-on effects can enable traders to react at pace and adjust strategies.  

Following the invasion of Ukraine, it became crucial to understand the security of supply chains for grain around the world, which was made possible through the analysis of alternative data, such as meteorological data and satellite imagery to estimate crop yields, highlighting the importance of extracting and correlating data from multiple sources. This is where NLP models also allow us to extract salient information pertaining to defined use cases from industry and national news sites, social media and official statistics. These can then be analysed and formulated into a ‘nowcast’ indicator that correlates with today’s material reality.  

Using AI to help commodity traders estimate supply and demand  

In the dynamic world of commodity trading, AI offers transformative insights through alternative data derived from a fundamental approach. For example, the "Quantcube Manufacturing Nowcast" utilises textual analytics and large language models (LLMs) to track real-time trends in manufacturing sectors across major global economies. By synthesising this data into a composite factor, traders can gain a comprehensive view of global demand for commodities such as crude oil, natural gas or aluminium. This approach not only enhances understanding but also provides a strategic edge in actively navigating those commodity markets.

Similarly, the QuantCube Drought Index, crafted as a proactive indicator of crop production, along with the Wheat Crop Yield Prediction—employing weather forecasts and satellite data—enables a detailed, real-time analysis of how phenological events are impacting regional crops worldwide. These tools offer invaluable assistance to soft commodity traders, equipping them with the knowledge to achieve outstanding performance in their market operations.

Importantly, each of the above use cases have not been delivered by artificial intelligence tools but rather informed by them.

Refining macroeconomic intelligence

A data scientist’s work is never done. No model should ever be considered complete, as they are always works in progress. There is always more data, intelligence and ingenuity that can be applied to refine models and the indicators they inform. By measuring daily and assessing nowcasts against official statistics, data scientists will always be able to get closer to the material reality.

With the evolution of the Internet of Things (IoT) and the natural proliferation of statistical information, there is more data than ever available for the construction and refinement of models. As new data comes online, data science teams will experiment, validate and deliver increasingly accurate insights for investors. IoT is improving the accuracy and quality of information, enabling us to extract better signals from the noise related to various use cases. Much like weather monitoring stations, that deliver real time measurements of temperature, wind velocity, humidity and atmospheric pressure, IoT devices are delivering real time telemetry pertinent to the understanding of macroeconomic variables.

When combined with models that enable sentiment analysis, contextual data extraction and image and audio reconstruction, the possibilities are endless. For instance, we can use textual analytics models to measure supply and demand in the construction industry by analysing social media and industry websites. It is also possible to extract text from videos or transform satellite images into an economic time series relating to NO2 emissions, drought conditions or real estate construction estimates.

Of course, when the insights delivered by these indicators are combined, it is possible to understand the full breadth of the macroeconomic situation and its impact on key commodities on a global, national and regional level. In each case, AI-derived insights will always be the servant and not the master—with human intelligence responsible for trading decisions. But the value of AI in enabling crucial insights to be derived faster than ever from alternative data to empower investment strategies simply cannot be ignored.