18:00 - 18:30 - Gathering beer & pizza
18:30-19:00 - How to Make Large Scale Predictions - Matomy
Making large scale predictions may differ significantly from “normal” predictions. Training your model on millions of observations requires not only the use of a different toolbox, but sometimes a whole different approach. In this talk, we will go through some sample use cases of predictions in the hundreds of millions, training the models and running them on a large scale.
Itai Blitzer, Ph.D., Head of Data at Matomy - As the Head of Data, Itai is responsible for Matomy’s DMP predictive profiles, currently covering over a billion user profiles, and processing over 20TB of new data arriving at Matomy’s servers each hour. Previously, he served as the Chief Data Scientist at Matrix.
19:00-19:45 - Deep dive to Amazon Redshift and Spectrum
Traditional data warehouses become expensive and slow down as the volume of your data grows. Amazon Redshift is a fast, simple, and cost-effective data warehouse that makes it easy to analyze all of your data using existing business intelligence tools. Amazon Redshift Spectrum is a new feature that extends Amazon Redshift’s analytics capabilities beyond the data stored in your data warehouse to also query your data directly in Amazon S3, with no loading needed. You can use Amazon Redshift and your existing business intelligence tools to run SQL queries against Exabytes of data, and Redshift Spectrum applies sophisticated query optimization, scaling fault-tolerant processing across thousands of nodes so results are fast – even with large data sets and complex queries. Join us to learn about the architecture of Amazon Redshift Spectrum, and how you can easily achieve faster analytics at a lower cost by leveraging strategies to partition and compress your data, in addition to supported columnar file formats.
Maor Kleider is a Senior Product Manager for Amazon Redshift, a fast, simple and cost-effective data warehouse. Maor is passionate about collaborating with customers and partners, learning about their unique big data use cases and making their experience even better.
Ippokratis Pandis is a Principal Engineer at Amazon Web Services currently working on Amazon Redshift. Ippokratis is the architect of Amazon Redshift Spectrum and has been developing Amazon Redshift to enable customers to query all of their data in the format of their choice, in a fast, easy and cost-effective fashion.
19:45 - 20:00 Open Stage
[masked] to submit a talk
Thank you to TLV Partners for hosting