medium10 pts · first answer countsmodel-servingmlops
Same model, worse online scores
Offline evaluation is strong, but online predictions are poor. You find that "average spend last 30 days" is computed in SQL for training and differently in the API code for serving. What is this called?
Discussion 0
Join free to post in the discussion.
Related questions
- When batch inference fitsMLOps Engineer
- Traffic before the model has loadedMLOps Engineer
- Why export a model to ONNXMLOps Engineer
- Protocol for internal inference callsMLOps Engineer
- What continuous training isMLOps Engineer
- Manual process maturityMLOps Engineer
- Latency and throughputMLOps Engineer
- What TTFT measuresMLOps Engineer