EconML package failing the latency in Production
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 4.8k
- Forks
- 827
- PR merge metrics
- No merged PRs in 30d
Description
Hi Team - We have worked on building a CausalForestDML on EconML package and want to take it to Production. However, we are failing in terms of meeting the latency requirement by running the .effect function to get the heterogenous treatment effect. Current latency is coming around ~20ms whereas the same number for xgboost is around 2-3 ms. Our hypothesis is that .effect function is optimal for doing the batch prediction whereas when we do a single row prediction, time increases. Is there any way to optimize it to reduce the latency of the current model.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by profiling the CausalForestDML .effect function for single-row and batch predictions, using the reported ~20 ms and 2–3 ms XGBoost timings as the comparison. Determine which part of the prediction path causes the latency gap; done means a validated optimization that meets the production latency requirement.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, performance
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100