We’re glad to announce our second DataConnect meetup in NYC!
Jeremy Salfen, Director of Data at Kickstarter, will explain how his team built its recommender system from scratch and give attendees tips and tricks to help them create their own.
Guilherme de Oliveira, Data Scientist at Dataiku, will present a use case on recommender engines using a dataset involving beer check-ins in New York.
Lessons Learned from Building a Recommender System:
Kickstarter’s data team built its project recommendations with the following mindset: start simple and only add complexity when necessary. From a query with under 10 lines of code to a micro service running an ensemble of collaborative filtering and content-based models, Jeremy and his team developed their system almost entirely from scratch, iteratively building and learning from the results. You will learn about the algorithms they used, the infrastructure they built, and the experiments they run to validate their effect on the user experience.
Jeremy (http://www.linkedin.com/jsalfen) is Director of Data at Kickstarter. His current focus is building data products to improve Kickstarter's user experience and refining the company's approach to the design and analysis of experiments. You can follow him on Twitter at @jsalfen (https://twitter.com/jsalfen).
Guilherme (https://www.linkedin.com/in/gdeoliveira/) is a Data Scientist at Dataiku. He works out of the headquarters in NYC where he helps customers build and deploy predictive applications. Before joining Dataiku, he was a fellow at the Insight Data Science Fellowship program, and prior to that he worked in quantitative finance. He holds a PhD in applied mathematics.
6:00 PM: Pizza, beer, & networking
6:30 PM: Jeremy's presentation
7:00 PM: Guilherme’s presentation
7:15 PM: Q&A
7:30 PM: More pizza, beer, & networking
PS: Kickstarter is hiring! Check out their career page (https://www.kickstarter.com/jobs) for open positions.
PPS: Our DataConnect meetups 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.
Want to collaborate with us? Get in touch! (https://pages.dataiku.com/collaborate-with-dataiku-to-uplift-data-science-community)