I'm part of trivago's Data Engineering team where we are running a data processing pipeline through kafka, hadoop, impala and R processing roughly 7 billion events per day. Our hadoop cluster is central for BI dashboards, reports, ad hoc analyses, personalisation, bidding and recommendation algorithms as well as our invoicing.
|Kafka Streams and Protobuf
stream processing at trivago
|Saturday||H.2213||HPC, Big Data and Data Science||17:30||17:55|