{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Retailgentic | Consumer Behavior & Retail Trend","title":"A Conversation with Luca Fiaschi of PyMC Labs: Synthetic Consumers & the Future of Product Testing","html":"","width":"100%","height":180,"duration":3230,"description":"In this episode of Retailgentic, Scot sits down with Luca to unpack a research paper that blends academic rigor with real-world implications:\n“LLMs Reproduce Human Purchase Intent via Semantic Similarity licitation of Likert Ratings.”\nThe paper, co-authored with Colgate-Palmolive researchers, explores whether AI can accurately simulate human reactions to product concepts, enough to replace or accelerate traditional consumer panels, which are slow, expensive, and hard to scale.\nThis one goes deep, but in ways that any retail or AI leader should care about. Scot and Luca discuss:Colgate’s Challenge: How to test product concepts faster and at scale.Synthetic Consumers: AI models that react to products like human panels.Accuracy Breakthrough: Reaching ~73–74% agreement with real consumers.Fixing LLM Failure Modes: Why naive prompts don’t work, and what does.Bayesian Reasoning: Adding uncertainty so AI stops being confidently wrong.Smarter A/B Testing: Using AI to pre-screen ideas before running live experiments.Digital Clones: Future consumers earning money by sharing preference data safely.Simulated Populations: Matching real audiences for testing and predictions.AI isn’t just helping brands write copy or generate images, it’s beginning to think like their customers. If synthetic consumers continue to evolve at this pace, product development, A/B testing, and personalization may look completely different in just a few years.\nTimestamps:\n03:00 — Luca’s background: Rocket Internet, HelloFresh, Lazada, Stitch Fix\n08:00 — How PyMC Labs was founded & why Bayesian modeling matters\n16:00 — Bayesian thinking explained in simple terms\n19:00 — High-stakes decisions & why probabilistic reasoning matters\n24:00 — Colgate’s challenge: testing product concepts at scale\n26:00 — How synthetic consumer panels work\n30:00 — Accuracy results: humans vs. AI (~73–74%)\n32:00 — Why naive LLM prompting fails (“mode collapse”)\n35:00 — How reasoning → scoring solves accuracy issues\n38:00 —...","thumbnail_url":"https://img.transistorcdn.com/jyq4gzL8GtJPwkKazAV0YqDIJx5HXtdIt_4jcLqe_8A/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9lNThm/NDdlNDU0ODM5MTMx/YmM5NDcyYjM5YTNh/YjEzYS5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}