Crunch, Data Conference, October 16-18, 2019 Budapest

Meet the man behind your News Feed – Interview with Akos Lada

Dorina Szabadi // 2019-08-15

Every time you open your News Feed, you can see the most relevant content at the top. But do you know the process that organizes the stories from your friends and groups? Akos works at Facebook, where he leads the Feed and Stories Relevance Data Science team. He and his team work on key user-facing product algorithms: news feed ranking, stories ranking and notifications ranking. We're proud to introduce him as a speaker at Crunch Conference's Data Science track! It's time to meet the man behind your News Feed.

Crunch Conference: Which article/podcast/book/paper/cartoon/etc had the most powerful impact on your professional life and what was your takeaway?

Akos Lada: A likely somewhat unusual answer: I came over into data science because I was always very interested in high-level quantitative social science questions, and there’s some fascinating literature on this. As an economics undergraduate student, I chanced upon Daron Acemoglu and James Robinson’s work entitled ‘Economic Origins of Dictatorship and Democracy’. It’s a seminal book on institutions that describes how formal and informal rules and customs governing societies lead to their success or failure. I loved the work and James Robinson later even became one of my key advisors in graduate school.

CC: What do you think is a buzzword that we should forget and why?

AL: Tech bubble - it’s too generic and vague to mean anything.

CC: What technology or breakthrough do you hope we will be discussing five years from now?

AL: Self-driving cars: I actually think people under-predict how close we are to having them.

CC: What is your advice for data scientists entering the field?

AL: Learn quantitative skills (statistics, coding, ML), but also make sure you are asking a relevant and important question from the users’ point of view whenever you work, and try to keep solutions simple and understandable.

At the highest level, ranking has four elements: the available inventory of stories; the signals, or data points that can inform ranking decisions; the predictions we make, including how likely we think you are to comment on a story, share with a friend, etc; and a relevancy score for each story. Akos's talk will describe how all these elements fit together to create the ranking that delivers the most value to our 2bn+ users.

Spread the knowledge