50:44
Ingest & Stream Processing - What Will You Choose?
Pat Patterson and Ted Malaska talk about current and emerging data processing technologies, and the various ways of achieving "at least once" and "exactly once" timely data processing.
30:55
Journey from Data Integration to Data Science
Michael Wise discusses the journey from having data integrated across an organization, to employing data science to make good use of it.
01:26:12
Data Driven Action: A Primer on Data Science
S Aerni, S Ramanujam and J Vawdrey present approaches and open source tools for wrangling and modeling massive datasets, scaling Java applications for NLP on MPP through PL/Java and much more.
50:40
Data Structure Adventures
Joseph Blomstedt presents ongoing work to build a new set of high performance data structures for Erlang, including both single process data structures as well as various concurrent data structures.
59:25
Making Distributed Data Persistent Services Elastic (Without Losing All Your Data)
Joe Stein introduces Mesos and managing data services on it, presenting use cases for replacing classic solutions (like cold storage) with new functionality based on these technology.
53:01
Design vs. Data: Enemies or Friends?
Big Design Upfront was considered so evil in the early days of Agile that it acquired its own acronym. It’s time we relearned that great products start with asking the right questions.
39:31
Responding Rapidly When You Have 100GB+ Data Sets in Java
Peter Lawrey discusses data-driven reactive systems, profiling latency distribution in such an environment, finding rare bugs, implementing resilience and monitoring.
47:40
Evolving a Data System
Simon Metson approaches the problem of evolving a data system; some patterns and anti-patterns both technical (polyglot systems, lambda architectures) and organisational (data silos, lava layers).
48:23
Don’t Let Data Gravity Crush Your Infrastructure
Dave McCrory talks about what is Data Gravity, how it affects performance and portability and why these effects are amplified when there are larger volumes of data.
46:52
Consistency without Consensus: CRDTs in Production at SoundCloud
Peter Bourgon provides a practical introduction to Conflict-free Replicated Data Types (CRDTs) and describes a production CRDT system built at SoundCloud to serve several product features.
59:37
Following Google: Don’t Follow the Followers, Follow the Leaders
Mark Madsen explains the history of databases and data processing over the past decades and looks where the industry will go.
44:52
Structure, Personalization, Scale: A Deep Dive into LinkedIn Search
The authors discuss some of the unique challenges they've faced delivering highly personalized search over semi-structured data at massive scale.
