February 12, 2020

265 words 2 mins read

Interactive sports analytics

Interactive sports analytics

Imagine watching sports and being able to immediately find all plays that are similar to what just happened. Better still, imagine being able to draw a play with the Xs and Os on an interface like a coach draws on a chalkboard and instantaneously finding all the similar plays and conduct analytics on those plays. Join Patrick Lucey to see how this is possible.
Talk Title Interactive sports analytics
Speakers Patrick Lucey (Stats Perform)
Conference Strata Data Conference
Conf Tag Make Data Work
Location New York, New York
Date September 24-26, 2019
URL Talk Page
Slides
Video Talk Video

Imagine watching sports and being able to immediately find all plays that are similar to what just happened. Better still, imagine being able to draw a play with the Xs and Os on an interface like a coach draws on a chalkboard and instantaneously finding all the similar plays and conduct analytics on those plays (i.e., when those plays occur, how many points a team expects from that play). Additionally, imagine having the ability to evaluate the performance of a player or a team in a given situation and compare it against another player in exactly the same situation. This approach is called interactive sports analytics, and Patrick Lucey explains methods to find play similarity using multi-agent trajectory data, as well as predicting fine-grain plays. You’ll see examples using tracking data amassed from the Stats Perform massive sports data archives. And you’ll learn how you can go beyond center-of-mass tracking (i.e., dots) and capture body-pose information from broadcast video to take analysis to the next level.

aws analytics video tracking performance
comments powered by Disqus
How to deploy large-scale distributed data analytics and machine learning on containers (sponsored by HPE (BlueData))

How to deploy large-scale distributed data analytics and machine learning on containers (sponsored by HPE (BlueData))

February 12, 2020

Anant Chintamaneni and Matt Maccaux explore whether the combination of containers with large-scale distributed data analytics and machine learning applications is like combining oil and water or like peanut butter and chocolate.
Trill: The crown jewel of Microsofts streaming pipeline explained

Trill: The crown jewel of Microsofts streaming pipeline explained

February 8, 2020

Trill has been open-sourced, making the streaming engine behind services like the Bing Ads platform available for all to use and extend. James Terwilliger, Badrish Chandramouli, and Jonathan Goldstein dive into the history of and insights from streaming data at Microsoft. They demonstrate how its API can power complex application logic and the performance that gives the engine its name.
Using Spark for crunching astronomical data on the LSST scale

Using Spark for crunching astronomical data on the LSST scale

February 8, 2020

The Large Scale Survey Telescope (LSST) is one of the most important future surveys. Its unique design allows it to cover large regions of the sky and obtain images of the faintest objects. After 10 years of operation, it will produce about 80 PB of data in images and catalog data. Petar Zecevic explains AXS, a system built for fast processing and cross-matching of survey catalog data.
From inception to insight: Accelerating AI productivity with GPUs (sponsored by Dell Technologies)

From inception to insight: Accelerating AI productivity with GPUs (sponsored by Dell Technologies)

February 5, 2020

Data scientists and machine learning engineers need the flexibility to work in multiple environments without wasting precious time configuring hardware and software and modifying code. Ramesh Radhakrishnan and John Zedlewski walk you through deploying a simple set of technologies for executing end-to-end pipelines entirely on GPUs.
Machine learning vital signs: Metrics and monitoring of AI in production

Machine learning vital signs: Metrics and monitoring of AI in production

January 27, 2020

Production artificial intelligence systems are interacting with the real world, and it's terrifying that oftentimes nobody has any idea how they're performing on live data. Donald Miner details why you should track your models in production over time, explains how you can implement proper logging and metrics for models, and details metrics you should probably be capturing.
Optimizing analytical queries on Cassandra by 100x

Optimizing analytical queries on Cassandra by 100x

January 26, 2020

Cassandra is one of the most popular datastores in big data and ML applications. Data analysis at scale with fast query response is critical for business needs, and while Cassandra with Spark integration allows running an analytical workload, it can be slow. Shradha Ambekar dives into the challenges faced at Intuit and the solutions her team implemented to improve performance by 100x.