The March Data SIG madness covers talks on sports analytics and understanding if an ML model is being fair or not? This month's meeting is graciously hosted and sponsored by Civis Analytics.
Measuring Model Fairness
by Henry Hinnefeld, Senior Data Scientist at Civis Analytics
When machine learning models make decisions that affect people’s lives, how can you be sure those decisions are fair? What does it even mean for an algorithm to be ‘fair’? As machine learning becomes more prevalent in socially impactful domains like policing, lending, and education these questions take on a new urgency.
By the end of this talk, you should be familiar with several common fairness metrics, be aware of the tradeoffs between them, and understand the subtleties of applying these metrics to real-world problems.
Divvy Data Deep Dive
by Chris Luedtke
Each day, Chicago's layout enables an incredible flow of people. Perhaps nothing bears this out better than 17 million Divvy rides over the past 6 years. In this talk, I present a pythonic approach to data sourcing, shaping, and mapping, culminating in a daily animation of all Divvy data to date.
U.S. Soccer: A Data-Driven Future
by Ted Morrison and Joris Bekkers
The U.S. Soccer Federation’s mission statement is clear and simple: to make soccer, in all its forms, a preeminent sport in the United States and to continue the development of soccer at all recreational and competitive levels. In the past twenty years soccer in the United States has seen impressive growth in participation, fan attendance, and television ratings. Due to this tremendous growth the Federation has embraced data-driven technologies to aid us in decision making, both commercial and sporting.
For this talk we hope to provide a glimpse into the thought processes and development of the analytical arm of U.S. Soccer Federation, the Research and Analytics Department.