BT
Older Newer rss
37:06

Predicting the Future: Surprising Revelations trom Truly Big Data

Posted by Pushpraj Shukla  on  May 24, 2016 Posted by Pushpraj Shukla  on  May 24, 2016

Pushpraj Shukla discusses how Microsoft Bing predicts the future based on aggregate human behavior using one of the largest scale data sets, and recent progress in large scale deep learnt models.

40:32

Netflix Keystone - How We Built a 700B/day Stream Processing Cloud Platform in a Year

Posted by Peter Bakas  on  May 19, 2016 Posted by Peter Bakas  on  May 19, 2016

Peter Bakas presents in detail how Netflix has used Kafka, Samza, Docker, and Linux to implement a multi-tenant pipeline processing 700B events/day in the Amazon AWS cloud.

41:26

Hunting Criminals with Hybrid Analytics

Posted by David Talby  on  May 10, 2016 Posted by David Talby  on  May 10, 2016

David Talby demos using Python libraries to build a ML model for fraud detection, scaling it up to billions of events using Spark, and what it took to make the system perform and ready for production.

47:42

Resilient Predictive Data Pipelines

Posted by Sid Anand  on  May 06, 2016 Posted by Sid Anand  on  May 06, 2016

Sid Anand discusses how Agari is applying big data best practices to the problem of securing its customers from email-born threats, presenting a system that leverages big data in the cloud.

35:44

Big-Data Analytics Misconceptions

Posted by Irad Ben-Gal  on  May 03, 2016 Posted by Irad Ben-Gal  on  May 03, 2016

Irad Ben-Gal discusses Big Data analytics misconceptions, presenting a technology predicting consumer behavior patterns that can be translated into wins, revenue gains, and localized assortments.

39:15

How Comcast Uses Data Science and ML to Improve the Customer Experience

Posted by Jan Neumann  on  May 01, 2016 1 Posted by Jan Neumann  on  May 01, 2016 1

Jan Neumann presents how Comcast uses machine learning and big data processing to facilitate search for users, for capacity planning, and predictive caching.

36:19

The Mechanics of Testing Large Data Pipelines

Posted by Mathieu Bastian  on  Apr 24, 2016 1 Posted by Mathieu Bastian  on  Apr 24, 2016 1

Mathieu Bastian explores the mechanics of unit, integration, data and performance testing for large, complex data workflows, along with the tools for Hadoop, Pig and Spark.

38:27

Stream Processing with Apache Flink

Posted by Robert Metzger  on  Apr 07, 2016 Posted by Robert Metzger  on  Apr 07, 2016

Robert Metzger provides an overview of the Apache Flink internals and its streaming-first philosophy, as well as the programming APIs.

43:44

Rethinking Streaming Analytics for Scale

Posted by Helena Edelson  on  Apr 03, 2016 Posted by Helena Edelson  on  Apr 03, 2016

Helena Edelson addresses new architectures emerging for large scale streaming analytics based on Spark, Mesos, Akka, Cassandra and Kafka (SMACK) or Apache Flink or GearPump.

01:30:26

Developing Real-time Data Pipelines with Apache Kafka

Posted by Joe Stein  on  Mar 04, 2016 Posted by Joe Stein  on  Mar 04, 2016

Joe Stein makes an introduction for developers about why and how to use Apache Kafka. Apache Kafka is a publish-subscribe messaging system rethought of as a distributed commit log.

01:24:27

Apache Spark for Big Data Processing

Posted by Ilayaperumal Gopinathan  on  Feb 14, 2016 Posted by Ilayaperumal Gopinathan Ludwine Probst  on  Feb 14, 2016

Ilayaperumal Gopinathan and Ludwine Probst discuss Spark and its ecosystem, in particular Spark Streaming and MLlib, providing a concrete example, and showing how to use Spark with Spring XD.

49:07

The Lego Model for Machine Learning Pipelines

Posted by Leah McGuire  on  Jan 16, 2016 Posted by Leah McGuire  on  Jan 16, 2016

Leah McGuire describes the machine learning platform Salesforce wrote on top of Spark to modularize data cleaning and feature engineering.

BT