[Deployment] 3.3 Design Approaches to ML System Architecture
in Development on API
What are Challenges and Key Principles for ML Systems
Design Approaches to ML System Architecture
General ML Archtecure Comparison
: Focus of this course Pattern 1(REST API) - best trade-off for most cases
| Pattern 1 (REST API) | Pattern 2 (Shared DB) | Pattern 3 (Streaming) | Pattern 4 (Mobile App) | |
|---|---|---|---|---|
| Training | Batch | Batch | Streaming | Streaming |
| Prediction | On the fly | Batch | Streaming | On the fly |
| Prediction result delivery | Via REST API | Through the shared DB | Streaming via Message Queue | Via in-process API on mobile |
| Latency for prediction | So so | High | Very Low | Low |
| System Management Difficulty | So so | Easy | Very Hard | So so |
