Deploying Machine Learning Models with Pulsar Functions
November 21, 2022
10:40
09:50
Hall B
English

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 Kjerrumgaard
David Kjerrumgaard
David Kjerrumgaard
David Kjerrumgaard
David Kjerrumgaard
Developer Advocate
David Kjerrumgaard

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.

Cancellation Policy

Sponsor Cancellation:

In case of cancellation of the event, we will offer a full refund to all attendees and sponsors.

Attendee cancellations:

Up to 30 days prior to the event – 100% Refund 30-14 days prior to the event – 50% Refund No refund will be offered later than that.

Cancellation Policy

Sponsor Cancellation:

In case of cancellation of the event, we will offer a full refund to all attendees and sponsors.

Attendee cancellations:

Up to 30 days prior to the event – 100% Refund.
30-14 days prior to the event – 50% Refund.
No refund will be offered later than that.