Supply chain professionals have always depended on forecasting to help them balance supply and demand. With the maturation of artificial intelligence (AI) systems, predictive analytics have grown in importance. The difference between traditional forecasting and predictive analytics is granularity. The staff at Predictive Analytics World explains the difference this way: “Predictive analytics [goes] beyond standard forecasting by producing a predictive score for each customer or other organizational element. In contrast, forecasting provides overall aggregate estimates, such as the total number of purchases next quarter. For example, forecasting might estimate the total number of ice cream cones to be purchased in a certain region, while predictive analytics tells you which individual customers are likely to buy an ice cream cone.”[1]

The staff at Rapidminer notes, “In recent decades, predictive modeling has become an essential tool for many organizations, allowing them to make data-driven decisions and enhance their business operations.”[2] They add, “As competition gets fiercer and new challenges arise, enterprises have been left searching for new and improved techniques to be faster, smarter, and better than their competitors. One innovative technique shaking up the data science space is causal AI. … Causal AI is an emerging form of machine learning [ML] that strives to go beyond traditional ML models. While traditional techniques identify the extent to which multiple events are related, causal AI identifies the root cause of events by understanding the effects of any variables that may have led to it, providing a much deeper explanation of their true relationship.”

Causal Reasoning Goes Beyond Correlation

All analysts know that correlations can easily lead one to believe something that is not true. To highlight that point, Tyler Vigen, a Partner at Boston Consulting Group (BCG), started a site called Spurious Correlations. Vigen has shown, for example, that there is an annual correlation between the number of people who have drowned by falling into a swimming pool and the number of films in which Nicolas Cage has appeared and that the divorce rate in Maine correlates to the per capita consumption of margarine in the United States. Clearly, making decisions based on such correlations would be unwise. That’s why Causal AI is becoming so important. Mark van Rijmenam, founder of the Futurwise Institute, explains, “Causal AI is a new field that combines artificial intelligence and causal reasoning, aimed at providing more accurate predictions and decision-making. It works by understanding the underlying relationships between variables in data, similar to how humans use causal reasoning to understand the world.”[3]

He adds, “Causal AI is a type of artificial intelligence that focuses on identifying and analyzing causal relationships, unlike other AI techniques like machine learning and deep learning which focus on finding patterns in data. Causal AI uses a targeted and causal approach to make predictions and decisions based on a nuanced understanding of relationships between variables.” Moving from correlation to causation is not easy. Freelance writer Neil Savage explains, “Computers can be trained to spot patterns in data, even patterns that are so subtle that humans might miss them. And computers can use those patterns to make predictions — for instance, that a spot on a lung X-ray indicates a tumor. But when it comes to cause and effect, machines are typically at a loss. They lack a common-sense understanding of how the world works that people have just from living in it.”[4]

Causal AI provides the common-sense capability that other forms of AI lack. This capability is essential if computers are going to be relied upon to make decisions. Murat Kocaoglu, an electrical engineer at Purdue University, told Savage, “Anything beyond prediction requires some sort of causal understanding. If you want to plan something, if you want to find the best policy, you need some sort of causal reasoning module.” At Enterra Solutions®, we understand the importance of Causal AI as we advance the field of Autonomous Decision Science™ (ADS®) — a field that deals with data-enabled prescriptive and anticipatory analytics and insights for companies across a broad range of industries. Enterra® automates a new way of problem-solving and decision-making, going beyond advanced analytics to understand data, perform analytics, generate insights, answer queries, and make decisions at the speed of the market.

Causal AI and the Supply Chain

Jerry Stephens, General Manager of Supply Chain Management at causaLens, argues that Causal AI is becoming a necessity for smooth supply chain operations. He explains, “Prediction is at the core of running an efficient supply chain. Inventory management, in particular the prevalent challenge of stockouts for sustained periods, has made intelligent prediction more important than ever in enabling our vastly complex supply chains to operate in real time and deliver on customers’ needs. However, the current state of the art in machine learning relies on past patterns and correlations to make predictions of the future — which makes it prone to fail amid shifts in data distribution. The starting point for putting this right is shaking off the misconception that machine learning is synonymous with Artificial Intelligence; the real AI revolution only starts when machines can learn like scientists — looking at causal factors, as well as data, and making reasoned judgments for true intelligence in decision-making.”[5]

According to Stephens, “The need to understand the cause and effect of possible actions in order to affect desired outcomes has long been understood in fields such as economics and medicine, yet only recently has it begun to emerge in industry, let alone in the supply chain.” A few years ago, European academics Joris M. Mooij, Jonas Peters, Dominik Janzing, Jakob Zscheischler, and Bernhard Schölkopf wrote, “An advantage of having knowledge about causal relationships rather than about statistical associations is that the former enables prediction of the effects of actions that perturb the observed system. While the gold standard for identifying causal relationships is controlled experimentation, in many cases, the required experiments are too expensive, unethical, or technically impossible to perform. The development of methods to identify causal relationships from purely observational data therefore constitutes an important field of research.”[6]

Concluding Thoughts

Stephens concludes, “Next-level AI isn’t about being satisfied that predictions are right. It asks: are we making the right decisions? Can we infer the impact of our decisions? Do we know the root cause of our outcomes?” As van Rijmenam notes, “One way of looking at it is that by establishing cause-and-effect relationships between variables, causal AI provides a more complete and transparent understanding of how decisions are being made. This helps to make AI more explainable, as the reasoning behind decisions is clearer. … Causal AI can help to reduce the risk of unintended consequences.” In the future, Causal AI solutions will be “must have” technologies in order to remain competitive.

Footnotes
[1] Predictive Analytics World, “Predictive Analytics World FAQ“.
[2] Staff, “Causal AI,” Rapidminer, 2022.
[3] Mark van Rijmenam, “How Causal AI is Reshaping the World,” Datafloq, 6 February 2023.
[4] Neil Savage, “Why artificial intelligence needs to understand consequences,” Nature, 24 February 2023.
[5] Jerry Stephens, “AI for Supply Chains Needs Cause-and-Effect Reasoning,” SupplyChainBrain, 20 December 2022.
[6] Joris M. Mooij, Jonas Peters, Dominik Janzing, Jakob Zscheischler, and Bernhard Schölkopf, “Distinguishing cause from effect using observational data: methods and benchmarks,” ArXiv, 11 December 2014.