Building Internet-scale Recommendation Systems

​Data Phoenix team invites you to our upcoming webinar, which will take place on August 15 at 10 a.m. PT.

• ​​​​​​​​Topic: Building Internet-scale Recommendation Systems

• ​​​​​​​​Speakers: Maksym Lefarov (Senior Machine Learning Engineer at Spotify)

• ​​​​​​​​Participation: free (but you’ll be required to register)

​The talk explains the key stages in creating modern recommendation systems, including Candidate Generation, Ranking/Sequencing, and applying Business Rules. It covers how techniques like Collaborative Filtering and two-tower models help in understanding user preferences. The talk also discusses how to develop and deploy these models, focusing on the practical aspects of ML system design and MLOps. Additionally, it will touch on how auctions and marketplaces play a role in enhancing recommendations.

​​​Key Highlights of the Webinar:

• ​​Recommendations Systems

• ​Representations Learnings

• ​ML System Design

• ​MLOps

• ​Auctions/Marketplaces

​​​​Speaker

​Maksym Lefarov is working on Recommendation Systems, Cold-start, and Discovery problems at Spotify. Previously he was a Research Engineer at Bosch focusing on applying Reinforcement Learning to optimize manufacturing processes and continuous-control systems. Maksym’s professional interests span RecSys, LLMs, Reinforcement Learning, and MLOps.

​​Please join DataPhoenix Discord and follow us on LinkedIn and YouTube to stay updated on our community events and the latest AI and data news.