Netflix Director of Analytics Chris Pouliot on Movie Recommendations

On this episode of Big Data TV, David Feinleib interviews Chris Pouliot, the Director of Analytics and Algorithms at Netflix. The talk about the tools, technology, and business of making great recommendations.

Dave Feinleib: Hi, I’m Dave Feinleib here with another episode of Big Data TV. We’re here at Big Data Date Night. My guest is Chris Pouliot, Director of Algorithms and Analytics at Netflix. Chris, welcome to the show.

Chris Pouliot: Oh, thanks so much.

Dave: Chris tell us a little bit about what you do at Netflix.

Chris: I run a team of data scientists. It’s a horizontal data science team that spans across all of the business verticals. We’re trying to derive insights from Big Data, and help to make better business decisions, or help create a better user experience for our subscribers.

Dave: We’re all familiar of course with Netflix recommendations on the movies. What are some of the hard challenges you’ve faced in working with movies and data, and large numbers of users at Netflix?

Chris: Pretty much it’s just how do we get the data. Working with big data technology like our data’s in the cloud and Hive. Also figuring out how do we perform analytics on the Big Data. Exploring ways of how to use distributed machine learning algorithms in the cloud? What are the technologies that are out there, and how do we best utilize those to make our data science the most productive as it can be.

Dave: What are some of the challenges that you’ve had to overcome? Is it scale issues, is it diversity of data? What are some of the issues that you grapple with?

Chris: It’s a little bit of everything. Diversity of data, my team does not only personalizations for movies, but we also deal with content demand prediction. Helping our buyer down in Beverly Hills figure out how much do we pay for a piece of content. The personalization recommendations for helping users find good movies and TV shows. Marketing analytics, how do we optimize our marketing spin. Streaming platform, how do we optimize the user experience once I press play. There’s a wide range of data, so theres a lot of diversity. We have a lot of scale, a lot of challenging problems. The question then is, how do we attract great data scientists that can just see this as a playground, a sandbox of really exciting things. Challenging problems, challenging data, great tools, and then just the ability to have fun and create great products.

Dave: That’s terrific. Are you a big movie buff yourself?

Chris: Somewhat.

Dave: Any favorite movies we should know about from your viewing preferences?

Chris: Sure. Netflix is getting into creating original programming. Our first TV series is House of Cards starring Kevin Spacey with David Fincher producing it. Excellent show, I highly recommend it.

Dave: Excellent. Chris, thanks so much for being on the show, great to have you.

Chris: Thanks so much.

Leave a reply