Content Analytics with Spotify

Hello data science enthusiasts,

We’re excited to announce the launch of our series of DataConnect meetups in NYC! These regular after-work sessions are designed to provide you with insights from a wide range of industry experts, to bring together data professionals and enthusiasts to share insights, lessons learned, best practices, and to discover the latest technologies in the data ecosystem.

For the inaugural meetup, we’re honored to welcome Kenny Ning, Senior Data Scientist at Spotify. Kenny will explain what is Content Data & Analytics and give technical examples of his work in the field.

Henri Dwyer, Data Scientist at Dataiku, will deliver a complementary presentation on recommender systems, which are key to deliver the most targeted content proposition to the user.

https://secure.meetupstatic.com/photos/event/c/6/5/600_463503173.jpeg

Content Analytics in Theory & in Practice:

A tech company's success used to be "all about the product", but Kenny is here to argue that the content being served is equally, if not more, important to strategic success. You will learn about the relatively niche field that is "Content Data & Analytics" in the context of music, media, and entertainment and how it is driving the new wave of strategic thinking.

Kenny’s bio:

Kenny (https://www.linkedin.com/in/kenny-ning-5b00b460/) is a Senior Data Scientist at Spotify (http://www.spotify.com) working on the Content Insights (data & analytics) team. He is passionate about using technology, tools, and data to rewire how we think about music in the age of streaming.

____

Transfer Learning Applied to Recommendation:

Providing the best recommendations is an increasingly important part of companies' value proposition. One rich source of information is the visual aspect of the product. In the hotel business, some people prefer to see the inside of their rooms, whereas others prefer to see the nearby beach. In this talk, Henri will describe how he improved an e-business vacation retailer's recommendation system using the content of images and pre-trained deep learning models to derive user taste information. This transfer learning approach enables companies to use state of the art machine learning methods without requiring extensive deep learning investment.

Henri's bio:

Henri (https://www.linkedin.com/in/henridwyer/) is a Data Scientist and Engineer at Dataiku (http://www.dataiku.com). He has worked on varied machine learning problems and industries including recommendation systems, pharmaceutical industry projects and transportation. Henri enjoys reading the latest machine learning papers and seeing what can be applied in industry.

____

Agenda:

6:00PM: Pizza, beer, & networking
6:30PM: Kenny’s presentation
7:00PM: Henri’s presentation
7:15PM: Q&A
7:30PM: More pizza, beer & networking

PS: Spotify’s hiring! Check out their career page (https://www.spotifyjobs.com/job-category/data-analytics/) for open positions.

PPS: Want to collaborate with us to uplift the data community? Get in touch (https://pages.dataiku.com/collaborate-with-dataiku-to-uplift-data-science-community)