Join us for lunch and two analytics-related talks by practitioners or Columbia Faculty. Talks this time:
Garud Iyengar; Professor, IEOR, SEAS
Basketball Analytics - Using AI to Analyze Player Tracking Data in NBA games
In this talk we will discuss ongoing work on exploiting optical tracking data to develop new metrics to better characterize player strengths. One set of these metrics are based on understanding defensive assignment and automatic event detection. A second set is based on combining trajectory modeling with shot efficiency. Methodologically speaking, this work relies on hidden Markov models, logistic regression, deep neural nets, unidirectional and bidirectional Long Short Term Memory (LSTM) networks. The main innovation here is combining these machine learning techniques with domain knowledge.
Garud Iyengar is a Professor in the Industrial Engineering and Operations Research Department in the School of Engineering and Applied Science at Columbia University. He received his B. Tech. in Electrical Engineering from IIT Kanpur, and an MS and PhD in Electrical Engineering from Stanford University. His research interests are broadly in information theory, control and optimization. His published works span a diverse range of fields, including information theory, applied mathematics, computer science, operations research, and financing engineering. His current projects focus on the areas of large scale portfolio selection, sports analytics, quantitative marketing, smart grids, and systems biology.
Divyanshu Vats; Quantitative Researcher, Two Sigma Investments, Adjunct Professor, Columbia Business School
Machine Learning for Marketing
In this talk, I will give an overview of how Machine Learning can be applied to effectively solve the need for Marketing teams to have better customer segmentation. I will talk about some applications including reducing churn and predicting customer lifetime value. Finally, I will talk about some engineering challenges in deploying such Machine Learning systems on a large scale.
Divyanshu Vats is a Quantitative Researcher at Two Sigma Investments. He also teaches an analytics class at Columbia Business School. Before joining Two Sigma, Divyanshu worked at Sailthru as a Senior Data Scientist, where he designed and developed data-driven products using advanced Machine Learning to enable marketers to optimize customer lifetime revenue and customer engagement. He got his PhD from Carnegie Mellon University in 2011 and undergraduate degrees from UT Austin in 2006.