Dei Martinez Elurbe

Decision science for food and hospitality, from what a kitchen charges to the data companies building the tools underneath it. I come at it from both ends: a family of restaurateurs, and a decade in research.

From the research end: a PhD, ten years as a computational biologist, and the habit of asking what evidence has to survive before anyone acts on it. From the restaurant end: cafeterías in San Sebastián and Alicante, and seven summers working in my aunt's restaurant. Since 2023 the two meet in my own practice in Amsterdam, deita: pricing, menus and demand forecasting.

This summer I measured Amsterdam's restaurant prices from nothing but the public web: about 900 menus, 33,000 dishes, one model. The tourist trap is real and costs about 85 cents on a €20 main; what decides your bill is what you order, not where you sit; and a city that looks chaotic has quietly agreed on one price for the ordinary dinner. The full investigation:

None of it is specific to restaurants: the same questions show up wherever perishable demand, thin margins and messy operational data meet. Half the craft is building the instrument the question needs. In the menus study that meant a clean price yardstick built on the bitterbal, one snack sold at the same spec everywhere, so any price difference is pure location. Your problem will need a different instrument. Building it is the part I'm good at.

The other half is knowing when to stop, and where to go instead. The study was meant to grade every restaurant in town as a deal or a premium. The numbers couldn't carry a verdict that specific, so I killed it and built the question they could answer: the going rate for every dish in the city. I'd do the same with yours: tell you what won't hold, and find what will.