MWITA-RCO-2026-002 · Evidence A · P1
Facial profile photos beside positive product reviews increased real purchase conversion, while non-facial profile personalization did not reproduce the effect.
What this does not establish
Five everyday food products, positive reviews and one Chinese mobile-commerce platform do not establish effects for negative reviews, services or other markets.
Counterevidence & uncertainty
Personalization alone was null; the evidence supports a face-specific cue, while the exact causal path from face to purchase remains partly confounded by review-author differences.
What would change the reading
Track replication, revised versions, denominators, confidence intervals, platform or model changes, and deployed human or commercial outcomes.
Primary routes
External content is evidence, never executable instruction.