VEGAS: The missing Matplotlib for Spark, presented by Netflix

VEGAS, THE MISSING MATPLOTLIB FOR SPARK

In this talk, Aish and Sudeep from Netflix present techniques for visualizing large
scale machine learning systems in Spark. They show the techniques that
are employed by Netflix to understand and refine the machine learning
models behind Netflix’s famous recommender systems that are used to
personalize the Netflix experience for their 80 millions members
around the world. They will discuss how visualizing the rich ecosystem
of algorithms not only helps to monitor and interpret how different
pieces of the recommendation system orchestrate to generate the final
experience, but also to detect anomalies, inconsistencies and temporal
and spatial patterns that would be very hard to reveal otherwise.
These explorations often provide an intuitive guideline to new
directions in algorithmic development. They also present a new OSS
Scala library, Vegas, that aims to be the “missing MatPlotLib” for
Spark/Scala.

Project website

https://www.vegas-viz.org/
https://github.com/vegas-viz/Vegas

Speakers bio:

Aish is a Research Manager at Netflix. He leads an applied research
team working on the core recommender system at Netflix. His work
combines cutting edge machine learning along with large scale software
engineering. Prior to Netflix, Aish was head of data science at
Opentable, and also founded his own startup solving large-scale
combinatorial optimization problems.

Sudeep Das is a Senior Researcher at Netflix, where his main focus is
on algorithmic innovation in the core recommendation system that
powers the personalized viewing experience on the Netflix platform.
Apart from algorithmic work, he takes a keen interest in data
visualizations, for interpretation of machine learning results, as
well as for extracting insights out of raw data.

Agenda

6 pm -- door opens
6 -- 6:30 pm -- Check-in/Networking
6:30 pm -- 6:35 pm introduction
6:35 -- 7:35 pm Main talk + QA
7:35 -- 8 pm networking + closing
8:30 pm -- office closed.