## 🧩 Spaghetti → Schema

**Challenge 01** is the entry point to the *Grocery – Driven by Data* series and addresses the most fundamental problem in applied data science: before we can model, forecast, or automate, we must be able to *read the system we are working in*.

**Dr. V's Slide Decks :** [The Architecture of Validity](https://starshiptutor.substack.com/p/the-architecture-of-validity), [Challenge 01](https://starshiptutor.substack.com/p/challenge-01-spaghetti-schema-294), [Challenge 02](https://starshiptutor.substack.com/p/challenge-02-errors-integrity), [Challenge 03](https://starshiptutor.substack.com/p/challenge-03-data-signal)
**Meet the Avatars :** [Dr. Elena Vasquez](https://starshiptutor.substack.com/p/introducing-dr-elena-vasquez), [Evan Morales](https://starshiptutor.substack.com/p/introducing-evan-morales), [Maya Chen](https://starshiptutor.substack.com/p/introducing-maya-chen), [Daniel Reeve](https://starshiptutor.substack.com/p/introducing-daniel-reeve)
**Kaggle Pages :** Challenge 01, [Challenge 02](https://www.kaggle.com/competitions/challenge-02-errors-integrity-2026), [Challenge 03](https://www.kaggle.com/competitions/challenge-03-data-signal-2026)

##📐 Designing Clarity from Spreadsheets

**Dr. Elena Vasquez**, is a fictional Associate Professor of Information Science, who will introduce you to the challenges, while the other avatars will share your struggles in using and understanding them. 

Challenge 01 is designed to introduce students and practitioners to data as an operational artifact—shaped by human processes, informal workarounds, and organizational drift. The goal is not to “clean” data in isolation, but to construct **valid structure** inside a system that is already in motion.

Participants work with a fictional grocery chain, *North West Organics (NWO)*, presented explicitly as a **constraint generator**, not a toy dataset. The raw inputs consist of loosely coordinated spreadsheets with duplicated headers, inconsistent identifiers, drifting categories, and unreliable temporal fields. Rather than fixing symptoms piecemeal, participants must diagnose the system, reverse-engineer its conceptual model, and design a normalized relational schema that makes the data legible.

The core outcome of Challenge 01 is **legibility, not accuracy**. Through disciplined schema design, normalization, and reproducible ingestion pipelines, participants create a foundation that can be trusted, audited, and extended. This challenge establishes the architectural backbone for every subsequent stage in the series—data quality repair, forecasting, and strategy modeling. Structure comes first; trust follows. Without it, every downstream insight is fragile by design.