Big Data Moscow 2018


Sebastian Feduniak

Pattern Match, Poland


Software and Operations Engineer. Java expert, Erlang lover, DevOps and Cloud Computing practitioner with almost 10 years of experience in IT industry.


Amazon SageMaker in Practice

At re:Invent in 2017 Amazon announced new service – SageMaker, that allows you to build, train and deploy ML models at any scale. Sounds fantastic, but is it true?
We challenged the marketing taglines and decided to test a specific use case which is familiar to us: ad targeting.
During the workshop, which is an adventure itself, we build an approximation of an ad targeting system with the use of Amazon SageMaker – from development to deployment. We show how with use of such service you can start small and be pretty confident about scaling up and expanding the system later.
We start from the ground up, so no worries – there is no need for previous experience with advertising systems and neither AWS, although general knowledge about machine learning or data crunching is a plus. If you were curious after the last year’s re Invent announcement, that is a workshop for you!

Read more…

Date: October 11, 2018