Sean Owen provides examples of operational analytics projects in the field, presenting a reference architecture and algorithm design choices for a successful implementation based on his experience with customers and Oryx/Cloudera.
Matthew Moloney discusses using F# and .NET inside Excel, demonstrating doing big data, cloud computing, using GPGPU and compiling F# Excel UDFs.
Details on Pinterest's architeture, its systems -Pinball, Frontdoor-, and stack - MongoDB, Cassandra, Memcache, Redis, Flume, Kafka, EMR, Qubole, Redshift, Python, Java, Go, Nutcracker, Puppet, etc.
Indrajit Roy presents HP Labs’ attempts at scaling R to efficiently perform distributed machine learning and graph processing on industrial-scale data sets.
Rusty Sears introduces REEF along with examples of computational frameworks, including interactive sessions, iterative graph processing, bulk synchronous computations, Hive queries, and MapReduce.
Nick Kolegraff discusses common problems and architecture to support all the phases of data science and how to start a data science initiative, sharing lessons from Accenture, Best Buy, and Rackspace.
Jeff Magnusson takes a deep dive into key services of Netflix’s “data platform as a service” architecture, including RESTful services that: provide comprehensive metadata management across data sources (Franklin); enable visualization and caching of results of Hadoop jobs (Sting); and visualize the execution plans produced by languages such as Pig and Hive (Lipstick).
Crista Lopes writes a program in multiple styles -monolithic/OOP/continuations/relational/Pub-Sub/Monads/AOP/Map-reduce- showing the value of using more than a style in large scale systems.
Dan Frank discusses stream data processing and introduces NSQ – Bitly’s open source queuing system – and other new technologies used for communication between streaming programs.
Ken Collier discusses Agile Analytics, a combination of sophisticated analytics techniques, lean learning principles, agile delivery methods, and "big data" technologies.
Oleg Zhurakousky discusses architectural tradeoffs and alternative implementations of real-time high speed data ingest into Hadoop.
Mike Nolet shares lessons learned scaling AppNexus and architectural details of their system processing 30TB/day: Hadoop, load balancer-free DNS architecture built in GSLB and Keepalived, and real-time data streaming built in C.