As promised, we planned to have quarterly Flink meetup and now it's about the time. Thus, I'm happy to announce that the next Bay Area Apache Flink Meetup is scheduled on June 26 at Zendesk, 1019 Market Street in San Francisco.
6:30 - 7:00 PM Networking and Refreshments
7:00 - 8:30 PM Short talks
-- Flink use case for fraud detection at Zendesk (TBD)
-- Flink use cases at Pinterest - real-time experimentation and more (Parag Kesar and Ben Liu)
-- Use Flink with Fasttext to generate “semantic vectors” from text for similarity calculations (Ken Krugler)
Abstract: We then use Flink to combine these vectors with the original ad/web page data to build entity-level semantic vectors that can be used to calculate similarity between ads, advertisers, and publishers. I’ll talk about the challenges of using native Fasttext code with Flink, tricks used to efficiently join word-level vectors with the original data, and generating per-key (bucketized) output files in a batch workflow.