[TALK]@Telematika

Talks & Presentations Collection

Data science at eHarmony: A generalized framework for personalization
December 14, 2019

Data science at eHarmony: A generalized framework for personalization

Data science has always been a focus at eHarmony, but recently more business units have needed data-driven models. Jonathan Morra introduces Aloha, an open source project that allows the modeling group to quickly deploy type-safe accurate models to production, and explores how eHarmony creates models with Apache Spark and how it uses them.

Data science: A view from the White House

Data science: A view from the White House

December 14, 2019

Keynote by DJ Patil and Lynn Overmann
Decision 2016: What is your data platform?

Decision 2016: What is your data platform?

December 13, 2019

During election season, were tasked with considering the next four years and comparing platforms across candidates. Whats good for the country is good for your data. Consider what the next four years will look like for your organization. How will you lower costs and deliver innovation? Jack Norris reviews the requirements for a winning data platform, such as speed, scale, and agility.
Delivering near real-time mobility insights at Swisscom

Delivering near real-time mobility insights at Swisscom

December 13, 2019

Swisscom, the leading mobile service provider in Switzerland, also provides data-driven intelligence through the analysis of its mobile network. Its Mobility Insights team works to help administrators understand the flow of people through their location of interest. Franois Garillot explores the platform, tooling, and choices that help achieve this service and some challenges the team has faced.
Designing a location intelligence platform for everyone by integrating data, analysis, and cartography

Designing a location intelligence platform for everyone by integrating data, analysis, and cartography

December 13, 2019

Geospatial analysis can provide deep insights into many datasets. Unfortunately the key tools to unlocking these insightsgeospatial statistics, machine learning, and meaningful cartographyremain inaccessible to nontechnical audiences. Stuart Lynn and Andy Eschbacher explore the design challenges in making these tools accessible and integrated in an intuitive location intelligence platform.
Driving open source adoption within the enterprise

Driving open source adoption within the enterprise

December 13, 2019

Theres been much discussion on open source versus commercial; CIOs and CTOs are increasingly interested in solutions that blend the benefits of both worlds. Ron Bodkin explains how Teradata drives open source adoption inside enterprises through a range of initiatives: direct contributions to open source projects, building orchestration software, and providing technical expertise.
Elastic data services on Mesos via Mesospheres DC/OS

Elastic data services on Mesos via Mesospheres DC/OS

December 13, 2019

Adam Bordelon and Mohit Soni demonstrate how projects like Apache Myriad (incubating) can install Hadoop on Mesosphere DC/OS alongside other data center-scale applications, enabling efficient resource sharing and isolation across a variety of distributed applications while sharing the same cluster resources and hence breaking silos.
Evaluating models for a needle in a haystack: Applications in predictive maintenance

Evaluating models for a needle in a haystack: Applications in predictive maintenance

December 13, 2019

In the realm of predictive maintenance, the event of interest is an equipment failure. In real scenarios, this is usually a rare event. Unless the data collection has been taking place over a long period of time, the data will have very few of these events or, in the worst case, none at all. Danielle Dean and Shaheen Gauher discuss the various ways of building and evaluating models for such data.
Fast cars, big data: How streaming data can help Formula 1

Fast cars, big data: How streaming data can help Formula 1

December 13, 2019

Modern cars produce data. Lots of data. And Formula 1 cars produce more than their fair share. Ted Dunning presents a demo of how data streaming can be applied to the analytics problems posed by modern motorsports. Although he won't be bringing Formula 1 cars to the talk, Ted demonstrates a physics-based simulator to analyze realistic data from simulated cars.
File format benchmark: Avro, JSON, ORC, and Parquet

File format benchmark: Avro, JSON, ORC, and Parquet

December 13, 2019

Picking the best data format depends on what kind of data you have and how you plan to use it. Owen O'Malley outlines the performance differences between formats in different use cases and offers an overview of the advantages and disadvantages of each to help you improve the performance of your applications.
Five-senses data: Using your senses to improve data signal and value

Five-senses data: Using your senses to improve data signal and value

December 13, 2019

Data should be something you can see, feel, hear, taste, and touch. Drawing on real-world examples, Cameron Turner, Brad Sarsfield, Hanna Kang-Brown, and Evan Macmillan cover the emerging field of sensory data visualization, including data sonification, and explain where it's headed in the future.
From big data to human-level artificial intelligence

From big data to human-level artificial intelligence

December 13, 2019

Gary Marcus explores the gap between what machines do well and what people do well and what needs to happen before machines can match the flexibility and power of human cognition.
Google BigQuery for enterprise

Google BigQuery for enterprise

December 12, 2019

Chad W. Jennings demonstrates the power of BigQuery through an exciting demo and announces several new features that will make BigQuery a better home for your enterprise big data workloads.
Hadoop and Spark at ING: An overview of the architecture, security, and business cases at a large international bank

Hadoop and Spark at ING: An overview of the architecture, security, and business cases at a large international bank

December 12, 2019

Bas Geerdink offers an overview of the evolution that the Hadoop ecosystem has taken at ING. Since 2013, ING has invested heavily in a central data lake and data management practice. Bas shares historical lessons and best practices for enterprises that are incorporating Hadoop into their infrastructure landscape.
Hadoop application architectures: Architecting a next-generation data platform for real-time ETL, data analytics, and data warehousing

Hadoop application architectures: Architecting a next-generation data platform for real-time ETL, data analytics, and data warehousing

December 12, 2019

Jonathan Seidman, Gwen Shapira, Mark Grover, and Ted Malaska demonstrate how to architect a modern, real-time big data platform and explain how to leverage components like Kafka, Impala, Kudu, Spark Streaming, and Spark SQL with Hadoop to enable new forms of data processing and analytics such as real-time ETL, change data capture, and machine learning.
Hadoop in the cloud: A Nielsen use case

Hadoop in the cloud: A Nielsen use case

December 12, 2019

Cloudera CEO Tom Reilly and James Powell, global CTO of Nielsen, discuss the dynamics of Hadoop in the cloud, what to consider at the start of the journey, and how to implement a solution that delivers flexibility while meeting key enterprise requirements.
How a Spark-based feature store can accelerate big data adoption in financial services

How a Spark-based feature store can accelerate big data adoption in financial services

December 12, 2019

Kaushik Deka and Phil Jarymiszyn discuss the benefits of a Spark-based feature store, a library of reusable features that allows data scientists to solve business problems across the enterprise. Kaushik and Phil outline three challenges they facedsemantic data integration within a data lake, high-performance feature engineering, and metadata governanceand explain how they overcame them.
How the largest US healthcare dataset in Hadoop enables patient-level analytics in near real time

How the largest US healthcare dataset in Hadoop enables patient-level analytics in near real time

December 12, 2019

The need to find efficiencies in healthcare is becoming paramount as our society and the global population continue to grow and live longer. Navdeep Alam shares his experience and reviews current and emerging technologies in the marketplace that handle working with unbounded, de-identified patient datasets in the billions of rows in an efficient and scalable way.
How to achieve zero-latency IoT and FSI data processing with Spark

How to achieve zero-latency IoT and FSI data processing with Spark

December 11, 2019

Yaron Haviv explains how to design real-time IoT and FSI applications, leveraging Spark with advanced data frame acceleration. Yaron then presents a detailed, practical use case, diving deep into the architectural paradigm shift that makes the powerful processing of millions of events both efficient and simple to program.
Inbox is the Trojan horse of AI

Inbox is the Trojan horse of AI

December 11, 2019

When Hollywood portrays artificial intelligence, it's either a demon or a savior. But the reality is that AI is far more likely to be an extension of ourselves. Strata program chair Alistair Croll looks at the sometimes surprising ways that machine learning is insinuating itself into our everyday lives.
Lessons learned running Hadoop and Spark in Docker

Lessons learned running Hadoop and Spark in Docker

December 11, 2019

Many initiatives for running applications inside containers have been scoped to run on a single host. Using Docker containers for large-scale environments poses new challenges, especially for big data applications like Hadoop. Thomas Phelan shares lessons learned and some tips and tricks on how to Dockerize your big data applications in a reliable, scalable, and high-performance environment.
Machine-learning techniques for class imbalances and adversaries

Machine-learning techniques for class imbalances and adversaries

December 11, 2019

Many areas of applied machine learning require models optimized for rare occurrences, such as class imbalances, and users actively attempting to subvert the system (adversaries). Brendan Herger offers an overview of multiple published techniques that specifically attempt to address these issues and discusses lessons learned by the Data Innovation Lab at Capital One.
Model visualization

Model visualization

December 11, 2019

Though visualization is used in data science to understand the shape of the data, it's not widely used for statistical models, which are evaluated based on numerical summaries. Amit Kapoor explores model visualization, which aids in understanding the shape of the model, the impact of parameters and input data on the model, the fit of the model, and where it can be improved.
Modern analytics with Dell EMC

Modern analytics with Dell EMC

December 11, 2019

Data, your most precious commodity, is increasing at an alarming rate. At the same time, an emerging business imperative has made this data a component of your deepest insights, allowing you to focus on your business outcomes. Patricia Florissi explains why the recent formation of Dell EMC ensures that your analytics capabilities will be stronger than ever.
Open the black box: An executive guide to making unstructured data work in finance

Open the black box: An executive guide to making unstructured data work in finance

December 11, 2019

You need to think about financial data differently to solve the most pressing challenges for your organization. But how do you get to data-driven finance and risk using unstructured data? Michelle Bonat explains how unstructured data (words and text) can be used to solve critical challenges in finance and unlock opportunities.
Parquet performance tuning: The missing guide

Parquet performance tuning: The missing guide

December 11, 2019

Netflix is exploring new avenues for data processing where traditional approaches fail to scale. Ryan Blue explains how Netflix is building on Parquet to enhance its 40+ petabyte warehouse, combining Parquet's features with Presto and Spark to boost ETL and interactive queries. Information about tuning Parquet is hard to find. Ryan shares what he's learned, creating the missing guide you need.
Powering real-time analytics on Xfinity using Kudu

Powering real-time analytics on Xfinity using Kudu

December 10, 2019

Sridhar Alla and Kiran Muglurmath explain how real-time analytics on Comcast Xfinity set-top boxes (STBs) help drive several customer-facing and internal data-science-oriented applications and how Comcast uses Kudu to fill the gaps in batch and real-time storage and computation needs, allowing Comcast to process the high-speed data without the elaborate solutions needed till now.
SAS: More open than you might think

SAS: More open than you might think

December 10, 2019

Hadoop and its ecosystem have changed analytics profoundly. Paul Kent offers an overview of SAS's participation in open platforms and introduces SAS Viya, a new unified and open analytics architecture that lets you scale analytics in the cloud and code as you choose.