quarta-feira, abril 18, 2012

Luzes no meio do oceano de dados

Ao ler este artigo "Toothpaste, toilet paper, white matter, and jam: Clues for better decision making" (a foto do artigo é paradigmática... já imaginaram um estrangeiro a escolher vinho num corredor de um hipermercado português?), ao chegar a este ponto:
"Writers, content producers, and other media have long known that “Top 10″ lists attract eyeballs and attention. People crave simplicity they can digest and manage from an authoritative source.
The typical American makes about 70 decisions per day. 50% of CEO decisions are made in 9 minutes or less, and less than 12% take more than an hour to make.
We collectively spend a alot of time not just trying to gather and analyze information to help inform the decisions we are making, but trying to absorb the information that comes at us unexpectedly, where we are not directing the stream of content."
Fiz logo a ponte para o capítulo 21 "Intuitions vs. Formulas" de "Thinking, Fast and Slow":
"The research suggests a surprising conclusion: to maximize predictive accuracy, final decisions should be left to formulas, especially in low-validity environments. In admission decisions for medical schools, for example, the final determination is often made by the faculty members who interview the candidate. The evidence is fragmentary, but there are solid grounds for a conjecture: conducting an interview is likely to diminish the accuracy of a selection procedure, if the interviewers also make the final admission decisions. Because interviewers are overconfident in their intuitions, they will assign too much weight to their personal impressions and too little weight to other sources of information, lowering validity." 
...
"The important conclusion from this research is that an algorithm that is constructed on the back of an envelope is often good enough to compete with an optimally weighted formula, and certainly good enough to outdo expert judgment. This logic can be applied in many domains, ranging from the selection of stocks by portfolio managers to the choices of medical treatments by doctors or patients." 
É claro que depois destas citações tenho de acrescentar:
"I learned from this finding a lesson that I have never forgotten: intuition adds value even in the justly derided selection interview, but only after a disciplined collection of objective information and disciplined scoring of separate traits."

Sem comentários: