Data Science Economy 2019: Dawn of AI
2+ keynotes / 30+ talks
delivered from experts & practitioners

16th & 17th of May 2019, @KRAŠ Auditorium, Zagreb, Croatia
Head of Data Science, Zemanta, an Outbrain company, Slovenia

Davorin Kopič


Davorin Kopič is the Head of Data Science at Zemanta, an Outbrain company, based in Ljubljana, Slovenia. He holds a BSc degree in Computer Science and Artificial Intelligence from University of Sussex. His team is responsible for machine learning algorithms in real-time bidding, advertising campaign optimisation automation, fraud detection, large-scale data analysis, and similar systems.

Zemanta is building the most advanced native advertising platform in the world. Marketing agencies use their platform to run native advertising campaigns that reach millions of people every day. Davorin and his team are building machine learning algorithms which participate in hundreds of thousands of auctions for ad space every second. Those algorithms decide which ads to show to what user, and at exactly what price. Bidding produces terabytes of data daily, and as auctions are happening in real-time – before the user even loads the webpage – machine learning has to be extremely optimised, efficient and accurate. This is why they are using the latest technologies including Go, Kafka, Aerospike and Spark.

In July 2017, Zemanta joined Outbrain, the world’s largest content recommendation company.


Building an effective data science team

If your organisation is anything like ours, then data science teams have huge and direct impact on the business and bottom-line figures. So you have probably been asking yourself how to build an effective data science team..

In our team, we are developing machine learning algorithms that are powering hundreds of thousands of monetary micro-transactions every second. We buy online advertising space in real time. Therefore it is crucial we have a highly performant, motivated and adaptable data science team, ready to tackle interesting challenges.

In this talk I will share some of the learnings I gained while building a data science team from scratch, as well as some knowledge from other data science teams within the company:

  • why good hiring process is crucial and what to look for in candidates,
  • how our teams are structured,
  • how to keep track of progress,
  • why development of team members is essential,
  • keeping the communication channels open, …

Of course there is no silver bullet when it comes to building data science teams, but learning what works well for us might help you in your endeavours