Week 5 Observations
There are two aspects to forecasting. One is to understand well what happened in the past because past performance is correlated with future results. The other is to anticipate how the future will differ from the past.
Some people give up on the second aspect because it’s harder. Instead they drill down on the first, constantly refining their methods and metrics to measure the past and then apply those metrics based on their historic predictive utility. They focus on what is known, and how it can be a guide to the unknown.
But things change. The correlation between past performance and future results over a long enough timeline tends toward zero. A team whose metrics portend success this year will probably be better than a team whose metrics portend failure in 2022. But in 2040, what was projected in 2022 means nothing. Change is the rule, yet for many the first — and often only — aspect of forecasting targets the past.
Keep reading with a 7-day free trial
Subscribe to Real Man Sports to keep reading this post and get 7 days of free access to the full post archives.