Filter (clear filters)





Overview for customer 360

Saving Energy with Apache Spark and Toon

Toon, a leading European smart thermostat and energy display, enables users to control and monitor gas and electricity consumption in their homes. Using the energy data they collect from over 400,000 homes they have developed a new Energy Waste Checker app to give actionable advice to end users to ensure that they do not needlessly waste energy. In this talk  Stephen Galsworthy, the Head of Data Science at Toon, describes how their novel disaggregation algorithms are implemented in Spark and shows how Toon uses cloud-based big data processing to offer data driven services to hundreds of thousands of users.


Scaling Your Skillset with Your Data

Jarrett Garcia, the director, Software Service and Quality at The Nielsen Company covers Nielsen’s successful implementation of Spark and Databricks which has allowed Nielsen to scale its products and its Data Scientists’ skillsets.


Bringing Real-Time to the Enterprise with Hortonworks DataFlow

TELUS, Canada’s fastest-growing national telecommunications company, with $12.9B of annual revenue and 12.7M customer connections. Members of the TELUS team will walk through the implementation and workflow challenges they overcame, working with Hortonworks to connect Apache Hadoop, Apache NiFi and Apache Spark, within a secure enterprise environment.


Vegas, the Missing MatPlotLib for Spark

Learn how Netflix uses Spark for machine learning, monitoring and interpretation, detect anomalies, inconsistencies and temporal and spatial patterns.


Automated Machine Learning Using Spark Mllib to Improve Customer Experience

Sourabh Chaki a lead engineeer at [24]7-inc explains how they use Spark and Mllib for automated feature engineering and machine learning. He also discusses how they use Graphx to connect visitor information across different channels.


Real-time Personal Trainer on the SMACK Stack

Learn how a real-time personal trainer system known as Muvr heavily relies on Spark, Mesos, Akka, Cassandra and Kafka (SMACK stack). Also look inside the architecture of the entire muvr system, particularly the challenges of ingesting large volumes of data, applying trained models on the data to provide real-time advice to users and training & evaluating new models using the collected data.