New Coke

By the early 1980s, Coca-Cola had a problem it could see clearly in the data: in blind taste tests, more people preferred the taste of Pepsi. Coca-Cola's market share had been slowly eroding for years against a rival that consistently won head-to-head comparisons. So the company did something it had never done in its 99-year history — it changed the formula.

The research behind "New Coke" was extensive: over 200,000 consumers tested, and the new, sweeter recipe beat both the original formula and Pepsi in blind taste tests. On paper, this was about as data-driven a decision as a consumer brand could make. On April 23, 1985, Coca-Cola discontinued its original formula and launched New Coke as the only Coke there was.

The public reaction was immediate and furious — not about taste, but about loss. People weren't just drinking Coca-Cola; they'd grown up with it, associated it with specific memories, family, identity. Protest groups formed. The company received thousands of angry calls a day. Sales of New Coke lagged badly, not because it tasted worse in isolation, but because customers weren't evaluating a drink — they were mourning something familiar being taken away without their consent. Within about three months, Coca-Cola brought back the original formula as "Coca-Cola Classic," and New Coke quietly faded into a footnote.

The taste tests weren't wrong. They measured exactly what they were designed to measure: preference in a single, anonymous sip. What they couldn't measure was attachment — the part of a product's value that has nothing to do with the product itself. Some data tells you what people prefer. It doesn't always tell you what they'll forgive you for taking away.