In this talk I will present a technique for deploying machine learning models to provide real-time predictions using Apache Pulsar Functions. In order to provide a prediction in real-time, the model usually receives a single data point from the caller, and is expected to provide an accurate prediction within a few milliseconds.
Throughout this talk, I will demonstrate the steps required to deploy a fully-trained ML that predicts the delivery time for a food delivery service based upon real-time traffic information, the customer's location, and the restaurant that will be fulfilling the order.
David is a committer on the Apache Pulsar project, and also the author of "Pulsar in Action" and co-author of "Practical Hive". He currently serves as a Developer Advocate for StreamNative where he focuses on strengthening the Apache Pulsar community through education and evangelization. Prior to that he was a principal software engineer on the messaging team at Splunk, and Director of Solutions for two Big Data startups; Streamlio and Hortonworks.