Eric Wilson - 2014
In 1960, Heinz von Foerster calculated that the world’s population at any given time could be approximated by the simple equation
In 1960, Heinz von Foerster calculated that the world’s population at any given time could be approximated by the simple equation
N(t) = C / ( t(0) – t )
N is the population
t is time
C is a constant
t(0) is a “doomsday” when the population becomes infinite ( FYI the formula worked out, doomsday will be November 13, 2026).
This simple formula with 99% of the micro-variation could predict the world population from the year 1000 to 1970. Furthermore, a quadratic-hyperbolic equation of the same type accurately represented the increase in the GDP the same years.
We use forecasts and the past to predict actions and the future every day. Whether you are trying to make the best decisions for your fantasy baseball league, looking to pick the right horse to win in the third race, or simply filtering through the results of a Google search: you are forecasting and predicting the future using the past. Predictive analytics is used in science, marketing, financial services, health care, police work, retail, and all types of business. In business, predictive models can be created to find patterns in historical data to help identify risk and opportunities. It can create accurate forecast of future sales looking at nothing else but what was sold of the past several periods.
Even though a forecast or projection may seem implausible or fantasy in many ways it is also intuitive. Take a look at the example below (figure 1) and try to guess where the next point will fall. Overwhelmingly almost everyone predicts the next point will fall below the line and answer “C”.
The core of predictive analytics relies on capturing relationships between explanatory variables and the predicted variables from past occurrences, and exploiting them to predict the unknown outcome. Often the unknown event of interest is in the future, but predictive analytics can be applied to any type of unknown whether it is in the past, present or future. For example, identifying suspects after a crime has been committed, or credit card fraud as it occurs.
With the right data and analytics a large big box retailer can even predict when someone is pregnant and when they may be due. Such was the case for a Minneapolis father who found out, from Target of all places, that his fifteen year old teenage daughter was pregnant. After shopping at Target, the girl began receiving mail at her father’s house advertising baby items: diapers, clothing, cribs and other baby-specific products. Her father was incensed at the company’s attempts to “encourage” pregnancy in teens and complained to the management. Turns out that what Target was doing was collecting point of sale data and clustering that data and comparing to demographics. Through looking at past purchases, seeing patterns and descriptive models Target could make assumptions of what coupons to send what customers. A few days after the irate father called Target, an embarrassed dad phoned the manager back to apologize; it appeared his daughter actually was pregnant.
So can we apply these same principles and logic to the progression or predictions of behavior in education trends, business cycles, politics, religion, or even generations, cultures, and societies? Of course we can. This is not voodoo but taking sound principles, reason, and many time statistics and modeling to generate a probable conclusion.
Looking at the same graph with some additional information added (figure 2):
Now where do you think the next point will be, where do you feel like we are heading?
April 19th 1775 the shot heard around the world and the beginning of the Revolutionary War. Almost 86 years to the day on April 12th, 1861 Confederate forces under General P.G.T. Beauregard Union soldiers at Fort Sumter starting the Civil War. Exactly 80 years later on December 2nd, 1941 America was attacked and we entered World War II. This was a day that will live in infamy; until 75 – 82 years later when… It is not chance or accident that America has experienced great cataclysms or “Crises” about every 82 years or so. Looking back before the shot heard around the world and the founding fathers were signing the Declaration of Independence another 87 years just passed since the Anglo-American “Glorious Revolution” of 1689 and Independence Day. Go back a slightly longer period, and you reach the English naval victory over the Spanish Armada—a turning point in England’s history. Add another 80 years or so before that takes you to the end of the War of Roses, a bloody civil war whose passage enabled “Tudor” England to emerge as a modern nation state.
Looking backward we can also see patterns and episodes of spiritual and cultural awakenings tend to occur about halfway in between these eras of crisis. Go 45 years backwards from the Spanish Armada and you land near the end of England’s tumultuous Protestant Reformation. Go 45 years forward from 1929, the onset of the Great-Depression-World War II era, and you land in 1969, America’s Consciousness Revolution and the summer of love.
So what does this mean is next? We need to start to peel away this onion and look deeper into the data and patterns to find causal variables and what is driving these cycles and rhythms. We need to use principles, logic, and intuition to better understand what has happened and what will happen next. What we cannot do is ignore that a pattern exist. We know we can gain insights into the future by looking at the past. We cannot bury our head in the sands at pretend we do not see what is coming.
Now where do you think the next point will be, where do you feel like we are heading?
