Slides from my talk "Continuous Delivery Principles for Machine Learning" @indix @ScaleByTheBay #scaleSF slideshare.net/RajeshMuppalla…
Hi Rajesh - Nice slides. 1 question .. in your continuous ML pipeline when u r developing models how do you handle concept drifts (when statistical properties change in unforeseen ways) ? Because of seasonal variations, you may get skewed metrics that may affect your model.
Hi Debasish. Great question. Here's my reply - gist.github.com/codingnirvana/…. Hope it answers the question you had. Let me know if you need more details.
United States Trends
- 1. Sonny Gray 7,697 posts
- 2. Rush Hour 4 11.1K posts
- 3. Godzilla 21K posts
- 4. Chelsea 331K posts
- 5. Red Sox 7,438 posts
- 6. Dick Fitts N/A
- 7. Happy Thanksgiving 21.4K posts
- 8. Raising Arizona 1,025 posts
- 9. National Treasure 5,674 posts
- 10. 50 Cent 4,972 posts
- 11. Gone in 60 2,112 posts
- 12. Barca 118K posts
- 13. Giolito N/A
- 14. Clarke 6,440 posts
- 15. Muriel Bowser N/A
- 16. Brett Ratner 3,425 posts
- 17. Ghost Rider 2,502 posts
- 18. Valley Girl N/A
- 19. Lord of War 1,477 posts
- 20. #ThanksYouTube N/A
Loading...
Something went wrong.
Something went wrong.