Learnings from creating recommendation engines with Amazon Personalize

~~~Learnings from creating recommendation engines with Amazon Personalize ~~~ mit Christian Bonzelet

Personalisation is one of our key strategic focus areas in the next years. And I am happy to see the fruits of our first year in a lot of our products for the Bundesliga.
⚽ Starting with providing recommended articles in the official Bundesliga App to all of our fans.
🤝 Followed by introducing recommended media content for our media and license partners within our international product portfolio.
⭐ And finally a new star is born. The Bundesliga Next app is shipped with a 100% personalized Tik-Tok-like home feed to all of our fans.
All three recommendation engines are built upon Amazon Personalize from Amazon Web Services. I want to share some insights about my personal learnings on both technical and organisational level when building AI/ML based recommendation engines using Amazon Personalize.
We will cover some aspects like the difference of a typical software development process compared to a machine learning development process. We will dive deeper into the engine room of Amazon Personalize and explain why KPI definition and A/B testing is key to success.

~~~ Über den Speaker ~~~

Hi my name is Christian. I am working as an AWS Solution Architect at DFL Digital Sports GmbH. Based in cologne with my beloved wife and two kids. I am interested in all things around ️☁ (cloud), ‍👱💻 (tech) and 🧠 (AI/ML).

With 10+ years of experience in several roles, I have a lot to talk about and love to share my experiences. I worked as a software developer in several companies in the media and entertainment business, as well as a solution engineer in a consulting company.

I love those challenges to provide high scalable systems for millions of users. And I love to collaborate with lots of people to design systems in front of a whiteboard.

I use AWS since 2013 where we built a voting system for a big live TV show in germany. Since then I became a big fan on cloud, AWS and domain driven design.

~~~ Agenda ~~~

18:30 - 19:00 Uhr: Virtuelles Get Together
19:00 - 20:00 Uhr: Talk
20:00 - Ende offen: Virtuelles Get Together

The talk will be in german!/Der Vortrag wird in deutsch vorgetragen!
~~~~~~

Zur Durchführung des Online-Meetings verwenden wir „zoom” und dabei den Account der codecentric AG. Den Zoom-Link lassen wir euch rechtzeitig per Direktnachricht zukommen. Hinweise zur Datenverarbeitung findet ihr unter https://www.codecentric.de/datenschutzerklaerung “Audio und Videokonferenzen”.