The causal nature of global trade

Todd Moses
Oct. 21, 2023
13 min read

The 1987 stock market crash first revealed the global relationships among markets. Known as Black Monday, that day saw the Dow Jones Industrial Average (DJIA) plunge over 20% within a few hours. Once graphed, the pattern revealed startling similarities with the first Black Monday of 1929. The one credited with ushering in the Great Depression.


Unlike the 1929 crash that brought in the Great Depression to the United States, by the end of that October day in 1997, stock markets had fallen by 45.5% in Hong Kong, 41% in Australia, 31% in Spain, 26.45% in the United Kingdom, 22.68% in the United States, and 22.5% in Canada [Moses 2018].


Stock market losses that October hit $1.7 trillion globally as 19 out of 23 international markets experienced drops of over 20% for the month [Daniel 2023]. Thus, an interconnectivity on a global scale was experienced. One that has yet to be fully understood.


Market complexity and supply chains


After an exhaustive study, French Mathematician Benoit Mandelbrot concludes that global markets are an unfathomably complicated machine. "To all the complexity of the physical world of weather, crops, ores, and factories, you add the psychological complexity of men acting on their fleeting expectations of what may or may not happen-sheer phantasms." The result is a time series with a frequency of great extremes [Mandelbrot & Hudson 2006]. 


Inside the complexity of markets are the complexities of supply chains - "huge, complex networks composed of enterprises, information systems, material handling, and contractual relationships." Like their parent markets, they shift continuously at the mercy of global events [Handfield & Linton 2022].


Like markets, supply chains are cash in motion. These complex structures are about moving things from one place to another. Those managing such networks look at what is happening in the market as a predictor of trade risks [Handfield & Linton 2022].


Global trade risks


Moody's research details that political disruption, financial dependence, and exposure to natural disasters create high risk. Since supply chains are about managing cash flows, inflation is another critical aspect - especially when dealing with international trade. A relatively new concern is the threat of cyberattacks.


Globalization has increased the challenges of supply-chain risk management [Bailey & Barriball 2019]. The genuine concern is the hidden risks associated with the invisible parts of the supply chain. These are the areas that manufacturers are unaware of. For example, raw materials may originate outside of the recorded supply chain with exposure to risks unaccounted for.


Cause and effect


Unlike the experiment-driven sciences of chemistry, biology, and physics, researchers cannot reproduce previous financial conditions or business scenarios [Lopez 2023]. Instead, they must learn from past experiences, pinpointing causes of historical problems from the evidence discovered. For example, the cause of the 1987 Black Monday crash is still up for debate.


Despite the rapid advancement of AI over the past few years, current systems need to catch up when it comes to tasks where there is a need to understand the actual causes behind an outcome [Shekhar 2022]. The problem is that models learn from training data, and understanding cause-and-effect can only come from knowledge of the data-gathering process, not the data itself [Pearl 2008].


All a deep-learning application can do is fit a function to data [Pearl & Mackenzie 2018]. The application must learn a new prediction function each time the world changes. This is the issue many companies experience while trying to use deep-learning to forecast risk.


Causal AI


Causal AI is an artificial intelligence system that explains the cause and effect of events or phenomena. Alan Turing, the father of artificial intelligence (AI), proposed a classification system for cognitive systems based on the type of queries they can answer [Pearl 2018]. To address this, Pearl describes a ladder where

  • First is statistical and predictive reasoning

  • The second is interventional reasoning. The ability to predict what happens when a system is changed.

  • Third is counterfactual reasoning. The ability to ponder what would have happened if circumstances were different.


Most current AI systems never make it past the ladder's first rung. In contrast, Estimand uses a Causal AI system that addresses the third rung—one with the ability to process counterfactual reasoning. That is the ability to see how the system changes when the world changes.


The big picture


We must pull back from the details on a global scale to see the big picture [Dalio 2021]. Only after understanding this mega-macro perspective can we focus on the details. For example, before the 17th century, countries as we know them today did not exist. Instead, there were states, kingdoms, and empires.


The money, credit, and capital markets cycle. It begins with prosperity, cycles to greed, and ends with debt. The market collapses when the debts can no longer be served with hard money [Dalio 2021]. My study of market crashes showed that this cycle is the most significant contributor to catastrophic market conditions [Moses 2018].


As debts grow and more people go into debt to fund speculation, selling those debts eventually becomes impossible. When this happens, those manufacturing money increase the supply and devalue the currency. Ultimately, this will erode the buying power of the money supply until it too collapses [Dalio 2021].


Noise and signal


The problem with understanding risk is that it is hard to separate the noise from the signal in light of cycles. For example, a period of prosperity brings a form of gambler's fallacy. This is the false belief in the hot hand, which means the expectation of future winnings due to past performance—the setup for destruction.


This noise becomes more difficult to detect once promotion begins, either through direct advertising, social campaigns, or media news stories. One thing I discovered in my study of markets is that if a market is trending upward due to the work of promotion, watch out. This happened in 1929 with stockbrokers loaning money. It occurred again in 1987 with junk bonds. Then again, in 2008, with subprime mortgages.


The same occurs with countries and regions. A corporation looking for a port-of-call may be distracted by either the positive or negative connotations of the media. Sometimes, it is justified, and others, not so much. To understand which, one must be familiar with the cause and effect. 




Billionaire investor Ray Dalio declares, "the world is a complicated place." He continues with understanding the past as a "highly competitive game." Dalio's asset management firm, Bridgewater, makes billions by processing information on all major countries and markets. They calculate investment positions from the cause and effect of world events.


Estimand provides causal AI with thousands of data sets to provide the cause of effect of world events in light of global risk. This level of sophistication is simplified through easy-to-use interfaces and integrations with existing enterprise software. Now, corporations can have the same insight into global risk as the world's highest-performing funds.



  • Bailey, T. & Barriball, E. (2019) A Practical Approach to Supply-Chain Risk Management. McKinsey & Company.

  • Dalio, R. (2021) Principles for Dealing with The Changing World Order. Avid Reader Press

  • Daniel, W. (2023) Top strategist sees ‘echoes of the 1987 crash’ in today’s stock market. Fortune.

  • Handfield, R. & Linton, T. (2022) Flow: How the Best Supply Chains Thrive. University of Toronto Press

  • Lopez de Prado, M. (2023) Causal Factor Investing. Cambridge University Press

  • Mandelbrot, B. & Hudson, R. (2006) The (MIs)Behavior of Markets. Basic Books

  • Moody's Analytics. (2023) Top 10 Supply Chain Risks That Companies Face.

  • Moses, T. (2018) How Markets Crash. Fintech with Todd.

  • Pearl, J. (2008) Causality. NIPS 2008 workshop on causality

  • Pearl, J., & Mackenzie, D. (2018) The Book of Why. Basic Books

  • Rhoads, R. (2020) The VIX Traders Handbook. Harriman House

  • Shekhar, G. (2022) Causal AI - Enabling Data-Driven Decisions. Towards Data Science.

Navigating the global risk landscape: Unveiling a comprehensive supply chain ontology
Predicting Financial Crisis with Causal AI