In an earlier post about forecasting, I mentioned the work by Nassim Taleb on the concept of black swan. In his remarkable book, “The Black Swan”, Taleb describes at length the characteristics of environments that can be subject to black swans (unforeseeable, high-impact events).
When we make a forecast, we usually explicitly or implicitly base it on an assumption of continuity in a statistical series. For example, a company building its sales forecast for next year considers past sales, estimates a trend based on these sales, makes some adjustments based on current circumstances and then generates a sales forecast. The hypothesis (or rather assumption, as it is rarely explicit) in this process is that each additional year is not fundamentally different from the previous years. In other words, the distribution of possible values for next year’s sales is Gaussian (or “normal”): the probability that sales are the same is very high; the probability of an extreme variation (doubling or dropping to zero) is very low. In fact, the higher the envisaged variation, the lower the probability that such variation will occur. As a result, it is reasonable to discard extreme values in the forecasts: no marketing director is working on an assumption of sales dropping to zero.
Now, the assumption that a Gaussian-shaped curve’s fit with a potential distribution of outcomes will be the best fit is just that: an assumption. It is based simply on observation of the past. Never before have our sales dropped by 20%, 50% let alone 100%. 10, 20 or 30 years of data can confirm this (observation of the past on a large number of data). But this is only an observation of the past, not a law of physics. Now, if we reason theoretically, not historically, on sales trends, we must recognize that there are many situations in which sales can vary widely. A sudden boycott of our products, for example (Danish dairy products in the Middle East after the Muhammad cartoons), a tidal wave in Japan, which deprives us of an essential supplier, a technological breakthrough that makes our products obsolete (NCR in 1971), the collapse of the Euro, etc. Suddenly deprived of oxygen, our sales are collapsing.
This is the black swan. The reason is simple: sales, like many statistical series, do not follow a Gaussian distribution. The probability of a large variation may be relatively low, but the reality is that in fact it cannot be calculated, because the distribution is unknown and cannot be estimated (this is what economist Frank Knight calls true uncertainty). We can thus be in a year in which the extreme value radically changes the historical distribution. We are in the domain of “fat tails”, ie unlike normally distributed series, high values can have a high probability of occurring. For example, in finance, Taleb noted that 99% of the total variation in the value of portfolios of derivatives between 1988 and 2008 (20 years) occurred in one day, when the European Monetary System collapsed in 1992. Taleb calls environments prone to black swans “Extremistan”.
Extremistan is the area in which a value can change dramatically the sheer scale of the distribution (mean, standard deviation). For example, if you take 10 people and calculate the average of their wealth, it is very likely that if you add a 11th person, the new average will be very different. If you add Bill Gates, a billionaire, the average literally explodes to the point that the other values become negligible, and the standard deviation also explodes. If you do the test at the Davos summit, the standard deviation will be lower. If, on the contrary, you measure the average height of your subjects, adding a new subject will only change slightly the calculated average. The height, in contrast to the wealth, belongs to Mediocristan, the universe of small variations of standard deviation.
Taleb gives another example to explain the phenomenon, that of the turkey. Every day, the farmer takes care of the turkey: he feeds it, pampers it, and ensures its good health. For the turkey, everything is getting better by the day. Every day confirms the feeling that the farmer wants the good of the turkey, and this feeling is based on a statistical series that is longer and longer, with a clear trend: a steady improvement in the variable “weight”, which equals “living conditions”. Tomorrow will be better than today, which is invariably confirmed the next day. One day in late November, the situation changes radically, and the variable “living conditions” drops to zero, completely upsetting the trend of the series. Black swan for the turkey, Thanksgiving has arrived. This example may be funny (except for the turkey) unless when you realize that most of financial experts think just like turkeys. The U.S. real estate has always increased in value, so it will do forever. The Tunisian regime has always been stable, so it always will be. We use Gaussian reasoning in environments that are not Gaussian. We believe we live in Mediocristan while in fact we live mostly in Extremistan.
But Extremistan escapes prediction, even though black swans do not happen that often. So what to do? One approach recommended by Taleb is to minimize the consequences of black swans: if you cannot avoid prediction, maybe you can prepare for their occurrence, and take steps to reduce their impact, should they occur. Raise a Nuclear Power Plant enough above sea level if it is in the area of tidal waves, don’t have a single plant, but two in different geographic areas, etc.
Another approach, only partially helpful however, was mentioned by my colleague Milo in an earlier post on Gresham’s law of strategy, is modeling with Monte-Carlo simulation software and employing explicitly non-gaussian curves.
These models show, however, that reducing the impact of disturbances often involves the development of redundancies, which goes against the quest for optimization (which actually means “optimization for a stable environment”) that is required in modern management. It is as such difficult to accept by the leaders that will always be tempted to favor immediate return at the expense of the resilience of the business. More generally, building redundancies will not be enough. If forecasting really is not possible, we must accept and implement strategic tools that are not based on prediction. We call this non predictive strategy, a concept we will develop in future posts on this blog.
One final note: if you find this perspective on strategy, disruption and surprise interesting, why not subscribe to our blog.
Yet another brilliant post full of food for thought!
Never rely only on figures for forecasting. Figures are results of actions and actions are caused by positions and potentials.
A sound strategic analysis of customer demands, competitor strengths and ambitions, Porters remaining 4 forces, PEST-analysis and Boston Consulting Group matrix combined with a risk assessment may be more complex but provides better insight and more importantly facilitates timely and appropriate reactions when Black Swans do occur.
Thanks Phillipe for a brilliant post.
In some cases it is easy to identify Mediocristan from Extremistan such as height and wealth. Therefore, it is relatively easier to prepare with an appropriate response.
However, in other cases, it is only in the hindsight we discover that Mediocristan has turned out to be an Extremistan. That is where the real challenge seems to be. Taking each Mediocristan to be an Extremistan might lead to a costly inappropriate response (Apple sitting on billions of dollar of cash in part may be a response to a possibility of Extremistan, next potential block buster product delivering zero sales). While it helps to know that sometime we treat Extremistan to be a Mediocristan, as you pointed out, by definition (unforeseeable), Extremistan events are difficult to identify even if one has just occurred (past is no guidance for future).
Does it leave us with the ability to prepare for an objective (cost-benefit basis) appropriate response? Perhaps, not. Subjectively (based on risk appetite) appropriate response might be possible (e.g. those shareholders that are Extremistan risk averse may not punish/ or reward a firm holding excessive cash). Is this the best we can do with much celebrated learning about Extremistan? Or should we begin to treat every Mediocristan as an Extremistan, and accept the associated cost? Where does this leave us on action plane?
I will look forward to your post on non predictive strategy. In the meantime some other thoughts, how about “Stress Test (similar to VAR ec.)” (while we might not know the causes, we can create a world where key business variable such as sales, cash get highly impacted) to prepare a contingency plan? Is it possible? What would this contingency plan be like? … … …
Very interesting post on a intriguing theme. I have never heard of this theory before but it seems like another, of a few, new important intents to solve prediction needs of the unstable world today. More and more predicting views are emerging in the marketing world mainly because the business world is facing much uncertainty, particularly in the European and American markets.
What caught my eye of your post is the importance made on the Non-Predictive environmental elements and the phenomena that does not fit the “normal” effect. We do not have good or even enough models to understand these situations because we, in the occidental world, usually focus on cause-effect criteria, but some models are theories have been developed with an out-of-the-box conception. Quantic physics, music and loop theories are interesting to see in this matter. I myself have ventured and posted some of this ideas…
I will be waiting for your announced post on Non-predictive strategy and will be looking for the book by Taleb, who, not surprising is from the Middle East with a cultural background not so cause-effect oriented.
Thanks a million for the post
Pingback: Managing the unexpected – On the work of Karl E. Weick and Kathleen M. Sutcliffe « Silberzahn & Jones
The Extremistan/Mediocristan distinction was laid before us in The Black Swan and can only be interpreted as meta-guidance for applied mathematicians. Actually it was meta-nonsense for people who had never applied mathematics, never intended to apply mathematics, but wanted to think deep thoughts about other people who applied mathematics … but let’s set that aside and examine it on it’s merits.
Taleb presented a perfectly clear instruction manual. The world has linear and non-linear phenomena. But mathematicians have to be careful, he argued, not to use the wrong kind of mathematics. You wouldn’t want to use linear mathematics to model a non-linear problem best treated with fractals, power laws and so forth now, would you? And I suppose you wouldn’t want to use fractals to model a linear system either – though Taleb is highly skeptical that any exist so that is a decidedly less important topic.
Take web page popularity. It follows a Zipf distribution, landing it squarely in the groovy world of power laws. So it would be a massive mistake to try to apply linear mathematics to it, right? To me more precise I’d say it would be a massive mistake, a violation of Taleb’s universal principal no less, to apply Linear Algebra, much less a singular value decomposition which is about as close to the center of “linear mathematics” (to humor that ridiculous phrase) as one could surely get. Strange then, that Larry Page sought fit to do so when inventing Page Rank, the algorithm distinguishing Google from Yahoo that powered the greatest commercial success in recent history.
Pingback: Culture of risk vs. culture of uncertainty: a crucial management issue « Silberzahn & Jones
I disagree with the following statement made in this article:
“For example, if you take 10 people and calculate the average of their wealth, it is very likely that if you add a 11th person, the new average will be very different. If you add Bill Gates, a billionaire, the average literally explodes…”
If one adds an eleventh person, the new average is very likely to be NOT MUCH DIFFERENT, as it is very, very unlikely that this person will be Gates. How many Gates (or similar persons) are in this world? That one randomly picks Gates is so unlikely that it would be far beyond what is described as a Black Swan event, just as the likelihood that the moon collides with the earth. (yes, this is somewhat hyperbolic but not too much).
Thanks for your comment. That is the whole point: it is very, very unlikely, but not impossible that it will be Gates. That is what we call a low probability, but high impact event. You don’t get a subprime crisis that often. If you take the height, it is a plain impossible event. The difference is subtle, but fundamental.
If “unforseeable” is a main characteristic of a BLACK SWAN, then its connection to any forecast must assume that the BS is germane to the discipline it is applied to. Lightning might be a BS to a mental disturbance but not to cancer.
This said, what is the connection between the subprime crisis and a BLACK SWAN? If the full range of financial and economic historical data, had been used, this crisis could not only have been foreseen but should have, as a few astute people actually did. History shows whenever money was easily obtained at a very low price, a speculative bubble and its inevitable burst followed, as in 1873, 1932 and now. Thus, the notion of a BS is not applicable to our present crisis.
Valiant and, for about eighty years effective, efforts had been made in the early1930s to prevent a repetition of the present condition. These were emasculated during the last two decades by greed and lack of foresight.
• Don’t let politicians and experts hide behind the notion of a Black Swan or similar fig leafs.
Pingback: Crafting Non-Predictive Strategy, Part I: Deep Understanding Beats Prediction « Silberzahn & Jones
Pingback: Risk, Uncertainty and Black Swans: Theoretical Differences and Practical Implications | Silberzahn & Jones