COVID-19 has completely altered human behavior - the way that we shop, research, consume and act - causing big shifts in patterns of data. These shifting patterns mean that some AI models, which were previously working fine, are now no longer predicting with the same accuracy. This creates some big challenges for data scientists and engineering teams on how to detect which models have been affected and how to get these AI applications up and running in a seamless way to continue generating business value.
In this session we will take a deep dive into the methodologies that exist for concept drift remediation. We will discuss how to automatically monitor models to detect drift, how to harness automated tools for adjusting models, how to utilize online models that adapt to shifting data, and how to set up alerts and tracking error rates for ongoing monitoring. The session will include a live demo and a real customer use case.
Yaron Haviv (Iguazio)
As the co-founder and CTO of Iguazio, Yaron drives the strategy for the company’s data science platform and leads the shift towards real-time AI. He also initiated and built Nuclio, a leading open source serverless platform with over 3,400 Github stars and MLRun, Iguazio’s open source MLOps orchestration framework.