Colgate paper shows LLM roleplay can predict real purchase intent (SSR method)
BenBajarin · x · 2026-11-22
Colgate published a paper arguing LLMs can predict real purchase intent by roleplaying customers, potentially upending market research. Asking an AI to 'rate 1-5' yields safe middle-of-the-road answers, so the Semantic Similarity Rating method instead gives the model a demographic profile and product concept, collects its raw unfiltered thoughts, and uses a semantic model to translate those into ratings.
More from Research
- Ultra-fast SAT solvers could make verification loops an ordinary part of inference — _onionesque · 2026-11-22
- NBER study of 500k+ GitHub devs: coding agents boosted commits ~240% but releases only ~30% — Antique_Atmosphere97 · 2026-11-22
- ReSFlow rectifies categorical flows on statistical manifolds for one-step generation — jiqizhixin · 2026-11-22
- Ben Goertzel on the AI Riemann proof: 'a new era of math'—and math glory now belongs to those with tokens — bengoertzel · 2026-11-22
- LessWrong: looping boosts no-CoT reasoning far more than general skills in NVIDIA's Dory 4B — CFGeek · 2026-11-22
- "Hilbert's program vindicated": Lean brings us near a practical decision machine — teortaxesTex · 2026-11-22