Fresh data beats stale data for machine learning applications. In this presentation Chip Huyen, co-founder of Claypot AI discusses the value of fresh data as well as different types of architecture and challenges of online prediction, it will also cover the tradeoffs between latency, staleness, and cost.
Key topics covered:
• Use cases for real-time ML.
• Architectures well suited for online predictions taking feature computation, prediction, and request response times into consideration.
• How to overcome key challenges with online prediction systems, such as latency vs. feature freshness, accuracy, and streaming infrastructure management.
Presented by:
Chip Huyen is a co-founder of Claypot AI, a platform for real-time machine learning. Previously, she was with Snorkel AI and NVIDIA. She teaches CS 329S: Machine Learning Systems Design at Stanford. She’s the author of the book Designing Machine Learning Systems (O’Reilly, 2022).
#realtimemachinelearning #machinelearningchallenges #onlineprediction
![](https://s2.save4k.ru/pic/MXDgWyPlFPc/maxresdefault.jpg)