Review the legacy Microsoft Azure Data Scientist (DP-100) route, machine-learning lifecycle concepts, model operations, evaluation, monitoring, and the current AI-300 replacement path.
DP-100 is an older Azure Data Scientist route. Use this cheat sheet to preserve useful model-lifecycle concepts while checking whether AI-300 is now the better Microsoft route for machine-learning operations.
Use this as a route check. Review the older data-science scope, then compare the current AI-300 machine-learning operations page.
| Field | Detail |
|---|---|
| Issuer | Microsoft |
| Legacy route | Azure Data Scientist Associate |
| Exam code | DP-100 |
| Current status | Replacement guidance |
| Closest current exam | AI-300 Machine Learning Operations Engineer Associate |
| IT Mastery status | Exam-selection sample question page |
| Older DP-100 area | What still matters | Current-route trap |
|---|---|---|
| Data preparation | Data quality, feature preparation, splits, leakage, and repeatability | Treating notebook work as production-ready operations |
| Model training | Experiments, metrics, compute, reproducibility, and model selection | Optimizing a model without deployment and monitoring plans |
| Model deployment | Endpoints, scaling, security, and release controls | Ignoring rollback and version management |
| Evaluation | Metrics, test sets, drift, bias, and fitness for purpose | Choosing accuracy without understanding the objective |
| Operations | Monitoring, retraining, performance, incidents, and governance | Studying only model creation when AI-300 emphasizes operations |
| Distinction | How to decide |
|---|---|
| DP-100 vs AI-300 | DP-100 is the older data-science route; AI-300 focuses more on ML operations and GenAIOps. |
| Training metric vs business metric | Training metrics evaluate model behavior; business metrics decide operational value. |
| Data drift vs concept drift | Data drift changes input distribution; concept drift changes the relationship between inputs and outcomes. |
| Batch inference vs online endpoint | Batch processes groups of records; online endpoints serve real-time predictions. |
| Experiment tracking vs monitoring | Tracking records development; monitoring watches deployed behavior. |
Use the DP-100 exam page to check old data-science concepts, then move to AI-300 if your target is current ML operations. Classify misses by lifecycle stage: data, training, evaluation, deployment, monitoring, or governance.