OYM-4454 Continuous deployment of machine learning models | Devoxx

Devoxx UK 2019
from Wednesday 8 May to Friday 10 May 2019.

   Continuous deployment of machine learning models

Conference

Big Data & AI
Big Data & AI
Intermediate level

Auto Trader is the UK’s leading digital automotive marketplace. We receive 60 million cross-platform visits each month, while our ML-powered car valuations provide 5.5 million valuations a month to both consumers and dealers.

Continuous delivery practices are well established at Auto Trader, especially when it comes to deploying more traditional web applications. We are therefore keen to ensure that any new machine learning models we develop fit this way of working; reducing the time to live allows for more experimentation and reduces the cost of getting machine learning models into production.

This talk describes how we launched a suite of new machine learning models with the ability serve low-latency predictions in real time. These models are automatically retrained and redeployed using continuous deployment pipelines in our existing deployment infrastructure, making use of technology including Apache Spark, Airflow, Docker and Kubernetes. Since models are deployed without manual intervention, we developed a robust testing strategy to ensure deployments will not cause a drop in model performance, including accuracy and coverage.

Apache Spark   Kubernetes   Continuous Delivery   Machine learning  
Subscribe to Devoxx on YouTube
Edward Kent
Edward Kent
From Auto Trader

Edward is a Senior Developer at Auto Trader. Working in the Data Engineering team, he uses technologies including Spark, Kafka, Scala, Python and Java on a daily basis. Edward has a strong interest in transitioning models from prototype to production-ready and deploying them at scale. He received his PhD in Chemical Engineering and Analytical Science from the University of Manchester in 2013.


Paul Doran
Paul Doran
From Auto Trader

Paul is a Technical Lead at Auto Trader. Working in the Data Engineering team, he uses technologies including Spark, Kafka, Scala, Python and Java on a daily basis. Paul has a strong interest in applying lean/agile methodologies to Data Engineering. He received his PhD in Computer Science from the University of Liverpool in 2010.


Sign-in
Make sure to download the Android or iOS mobile schedule.