Can the speaker detect if anyone in the audience is shaking their phone? Can we do it in real time? Could we escalate that to thousands of phones? Yes, yes, yes!

As data volume and velocity continue to increase, the need for real-time processing is becoming more pressing. However, building real-time ML pipelines can be complex and time-consuming, requiring expertise in both ML and streaming application development. This talk will address this by introducing Quix Streams, an open-source Python library that makes it easy for data scientists and ML engineers to build real-time ML pipelines without having to learn the intricacies of building a streaming application from scratch. We’ll cover:

– the growing importance of real-time processing in today’s application stack
– a comparison of batch (databased centered) and streaming (real time) architectures
– the principles of streaming architectures: topics, pub/sub, scalation, etc.
– an overview of Quix Streams and its features

This talk is relevant for data scientists, ML engineers, and software engineers who are looking to adopt new technologies and practices in order to build real-time ML pipelines and stay current in their field.

Technical level: Technical practioner