Outliers vs drift — how do you distinguish?
mediumAnswer
- Outliers = individual points far from distribution; drift = the distribution itself shifts.
- Time-based test: (1) if score spikes then returns → outliers or anomalies.
- (2) if score persistently elevated → drift.
- Aggregate score over rolling window (24h).
- Individual outlier detection: Isolation Forest, LOF, autoencoder reconstruction error.
- Drift detection: aggregated PSI / MMD over batch.
- Both matter but require different responses.
Check yourself — multiple choice
- Same thing
- Outliers = individual far points (spike then recover); drift = distribution persistently shifts; rolling window differentiates + different responses required
- Random
- Only outliers
Outlier = point; drift = distribution; rolling window differentiates.
#monitoring#data-quality
Practise MLOps & Data Quality
215 interview questions in this topic.
Related questions
- What is data drift and how do you detect it?
- How is concept drift different from data drift?
- What is schema drift and how do you detect it?
- What is label drift and why does it matter?
- How is Population Stability Index (PSI) computed and interpreted?
- Why prefer Jensen-Shannon Divergence over KL for drift?