The Question
Something is wrong with the model. This series finds what.
On a single day in October 2008, the S&P 500 fell by a magnitude that the standard model of financial markets said should not occur once in the lifetime of the universe.
Seven years later, the Swiss Franc appreciated fifteen percent against the Euro in minutes, wiping out several brokerages and generating losses that no risk model in operation had flagged as possible.
In March 2020, the fastest bear market in history unfolded in twenty-three trading days. Stocks, bonds, commodities, and currencies moved in ways that Gaussian risk models classified as statistically impossible.
In April of the same year, crude oil traded at negative thirty-seven dollars per barrel. The mathematical model said the probability of this event was zero. Not approximately zero. Zero.
These are not exceptions. They are the rule.
Extreme events in financial markets do not occur once in a lifetime. They occur every year. In every market. On every continent. They have been occurring for as long as markets have existed. And the dominant mathematical framework of modern finance, the framework that says these events should be impossibly rare, has been unable to explain why.
The Assumption
For over a century, the foundational assumption of financial theory has been that markets are random. That each day’s return is independent of the last. That price movements follow the familiar bell curve. That extreme events are rare, risk is stable, and the past tells you nothing useful about the future.
This assumption was elegant. It was mathematically tractable. It allowed the construction of beautiful theories: the Efficient Market Hypothesis, the Black-Scholes options pricing model, the Capital Asset Pricing Model, Value at Risk, mean-variance portfolio optimisation. An entire intellectual edifice was built on the premise that markets are, at their core, random.
There was just one problem.
The data never agreed.
From the very beginning, researchers noticed anomalies. Returns were not normally distributed. Extreme events occurred far more often than the bell curve predicted. Volatility clustered: violent days followed violent days, quiet days followed quiet days. The tails of the distribution were too fat. The centre was too peaked. The autocorrelation structure was too persistent.
These findings were acknowledged, documented, and catalogued. And then, largely, they were set aside. The anomalies were treated as curiosities. Footnotes. Exceptions that did not quite invalidate the rule.
This series treats them as the evidence.
The Investigation
We assembled forty-one years of daily futures data across sixty-eight markets and eight asset classes. Equities, bonds, currencies, energy, metals, grains, softs, and meats. Every continent. Every major exchange. From 1984 to 2026.
We asked a series of questions. Each question builds on the last. Each answer narrows the field of possible explanations until only one remains.
Do markets carry memory? How deep is that memory? How fat are the tails? Is the pattern universal? What causes it? How does the mechanism operate? Has it always been this way?
The investigation follows the logic of a detective story. The clues accumulate. The suspects are eliminated. The evidence converges. And by the end, the case is closed.
The Map
Here is where the investigation goes.
Episode 1: The Random Walk Is Dead // We test the independence assumption and find it broken. Markets carry memory.
Episode 2: The Nile River’s Secret // We measure the depth of that memory using a method born on the banks of the Nile.
Episode 3: The Impossible Keeps Happening // We count every extreme event in the data. The bell curve is not slightly wrong.
Episode 4: The Fingerprint // We compare all three signatures across all sixty-eight markets. One pattern. No exceptions.
Episode 5: The Null World // We build a market with no feedback. The fingerprint vanishes.
Episode 6: The Dial // We sweep feedback from zero to maximum. The random walk shatters at a single threshold.
Episode 7: The Permanent Signature // We test temporal stability. Forty years. Five crises. The fingerprint survives everything.
Episode 8: The Architecture // We assemble seven lines of evidence into a unified framework.
Episode 9: The Verdict // The case is closed. Here is what we proved, and what it means.
The Stakes
This is not an academic exercise.
If the random walk is wrong, then Value at Risk is wrong. Capital reserves are mis-calibrated. Options are mispriced. Portfolios are under-protected. The risk models that govern trillions of dollars in institutional capital are built on a foundation that does not describe the world they are meant to measure.
If the random walk is wrong, there must be a reason. Not a collection of ad hoc reasons for each anomaly, but a single, structural explanation for why markets behave the way they do. A mechanism that produces memory, fat tails, and volatility clustering simultaneously. A mechanism that operates in every market, in every decade, across every asset class.
This series identifies that mechanism.
It is called feedback.
Markets are not random because participants observe price and react to it. Those reactions change price. The changed price is observed by other participants, who react in turn. The output of the system becomes the input. The loop between observation and action is the engine that drives everything we see in the data: memory, persistence, fat tails, universality, and the permanent departure from the random walk.
That is the thesis. The next nine episodes are the proof.
Begin
This series is designed to be read in order. Each episode builds on the evidence of the last. The argument is cumulative. The conclusion is categorical.
No advanced mathematics is required. Every technical detail is explained in plain language in the text, with full methodology available in the endnotes for those who want it. The charts speak for themselves. The numbers are drawn from real data, not simulations, not hypotheticals, not back-of-the-envelope estimates.
Sixty-eight markets. Forty-one years. 647,922 trading days. One question.
Are markets random?
This research series is drawn from The Fractals of Finance: Determinism, Adaptation and the Geometry of Markets
The book explores the full architecture of feedback, fat tails, and fractal structure in financial markets, and what it means for how we trade, invest, and understand risk.
Available now on Amazon in paperback, hardcover, and Kindle.
Want a practical field manual for trading trends and capturing outliers?
The Aussie Turtles Trend Following Guide: A Field Manual for Hunting Outliers adapts the timeless principles of the original Turtle traders into a systematic, rules-based approach for modern markets. Co-authored with Adam Havryliv.
Available now on Amazon in paperback, hardcover, and Kindle.