From 8ee8f1791f501d0cc8d8578f9c13c3e8c4bce809 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Tom=C3=A1s=20Ravalli?= Date: Tue, 6 Oct 2026 20:06:32 +0200 Subject: [PATCH] Link the Data Science at Camp Nou essay for context Co-Authored-By: Claude Opus 5.5 --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index c312746..e81b23b 100644 --- a/README.md +++ b/README.md @@ -127,6 +127,8 @@ An earlier version searched `0.5×–2.5×` base price, but no training row is p The engine was validated via **segment-based A/B tests**: a subset of seating zones used the dynamic engine (treatment), the rest stayed on static pricing (control). Tests ran across matches of varying importance to ensure the lift wasn't an artifact of any single event. The +6% revenue lift held alongside a +4% sell-through rate, confirming the engine found market equilibrium rather than simply over-charging. +For the wider context (how data science and experimentation worked in a stadium's ticketing team), see [Data Science at Camp Nou](https://github.com/0trm/data-science-at-camp-nou). + ## How the engine works