# The Skew

> Lab-perfect. Production-broken.

Canonical URL: <https://datadriven.io/problems/the_skew>

Domain: AI Coding · Difficulty: medium · Seniority: L5

## Problem

ML team's fraud model trains at 0.84 AUC offline and tanks online. We isolated it to feature `user_orders_last_24h` , offline backfills compute it correctly, but the online value at scoring time is consistently higher. Run tests/test_feature_parity.py to see the divergence on a known prediction. Find the time-leak in the offline pipeline (features/orders_24h.py) and fix it. Defend your fix: what's the upper bound on staleness you've now committed the team to?

## Related

- [All practice problems](https://datadriven.io/problems)
- [Mock interview mode](https://datadriven.io/interview/the_skew)
- [Data Engineering Interview Prep Guide](https://datadriven.io/data-engineer-interview-prep)
- [Daily Challenge](https://datadriven.io/daily)

---

Source: DataDriven (https://datadriven.io). DataDriven is the data engineering interview community. Live code execution in SQL, Python, and Spark sandboxes. Every feature is open to every member.