Automated Machine Learning in the Wild
by Claudia Perlich (Dstillery, USA)
supported by Alibaba
Machine Learning research is progressing at an ever-increasing pace. Fueled by technology advances commonly referred to as “Big Data”, all data related fields are teaming with scientific and applied activity: our communities explore new application areas, develop new learning algorithms, and continuously scale and improve optimization and estimation methods. But from an industry perspective, many of the most impeding challenges are entirely elsewhere. This talk takes a fresh look at the practical state of affairs in the context of running a large-scale automated machine learning system that supports 50 Billion decision daily on behalf of hundreds of digital advertisers. Some of the key lessons are 1) robustness beats peak performance almost always, 2) support for the constant dynamic fluctuations in the data stream is essential, 3) models exploiting unknowingly any weakness of your metrics, and finally 4) the fact that despite big data, the data you really want never exists.
About the Speaker
Claudia Perlich leads the machine learning efforts that power Dstillery’s digital intelligence for marketers and media companies. With more than 50 published scientific articles, she is a widely acclaimed expert on big data and machine learning applications, and an active speaker at data science and marketing conferences around the world.
Claudia is the past winner of the Advertising Research Foundation’s (ARF) Grand Innovation Award and has been selected for Crain’s New York’s 40 Under 40 list, Wired Magazine’s Smart List, and Fast Company’s 100 Most Creative People.
Claudia holds multiple patents in machine learning. She has won many data mining competitions and awards at Knowledge Discovery and Data Mining (KDD) conferences, and served as the organization’s General Chair in 2014.
Prior to joining Dstillery in 2010, Claudia worked at IBM’s Watson Research Center, focusing on data analytics and machine learning. She holds a PhD in Information Systems from New York University (where she continues to teach at the Stern School of Business), and an MA in Computer Science from the University of Colorado.
Website
https://sites.google.com/site/claudiaperlich/
Slides
https://recsys.acm.org/wp-content/uploads/2016/09/RecSys-16-Keynote-Perlich.pdf
Date
Saturday, Sept 17, 2016, 09:00-10:00
Location
Kresge Auditorium
Personalization for Google Now — User understanding and application to information recommendation and exploration
by Shashi Thakur (Google, USA)
At the heart of any personalization application, such as Google Now, is a deep model for users. The understanding of users ranges from raw history to lower dimensional reductions like interest, locations, preferences, etc. We will discuss different representations of such user understanding. Going from understanding to application, we will talk about two broad applications recommendations of information and guided exploration both in the context of Google Now. We will focus on such applications from an information retrieval perspective. Information recommendation then takes the form of biasing information retrieval, in response to a query or, in the limit, in a queryless application. Somewhere in between lies broad declaration of user intent, e.g., interest in food, and we will discuss how personalization and guided exploration play together to provide a valuable tool to the user. We will discuss valuable lessons learned along the way.
About the Speaker
Shashidhar (Shashi) Thakur is a Distinguished Engineer in the search team at Google. He led the team that brought the Google Knowledge Graph to search. He has previously worked on different aspects of search ranging from spam detection to core ranking. Most recently, Shashi leads the Google Now team, whose mission is to build a rich personalized understanding model of users and proactively bring high utility content to the user. Prior to Google, Shashi was a Distinguished Engineer at Synopsys Inc., working on algorithms behind tools that make digital chip design processes more efficient. He holds a PhD in Computer Science from University of Texas, Austin and a BTech in Computer Science from Indian Institute of Technology, Bombay.
Website
https://www.linkedin.com/in/shashidharthakur/
Date
Sunday, Sept 18, 2016, 08:30-09:30
Location
Kresge Auditorium
Peer Effects, Social Multipliers and Cascades of Human Behavior
by Sinan Aral (MIT, USA)
In this talk, I will survey empirical approaches to causal inference in networks and describe a series of largescale randomized experiments and causal observational studies of peer influence to explore the behavioral dynamics catalyzed by peer effects or social spillovers in human behavior and opinion formation. I will discuss the public policy implications of peer effects for bias in online ratings, social advertising, human health interdependence and the ability to generate cascades of behavior through peer to peer influence in networks.
About the Speaker
Sinan Aral is the David Austin Professor of Management at MIT, where he holds joint Professorships in the Sloan School of Management, the Institute for Data, Systems and Society and where he co-leads MIT’s Initiative on the Digital Economy. He was the Chief Scientist at SocialAmp, one of the earliest social commerce analytics companies (until its sale to Merkle in 2012) and at Humin, a social platform that the Wall Street Journal called the first “Social Operating System” (until its sale to Tinder in 2016). Sinan was the Scholar-in-Residence at the New York Times R&D Lab in 2013, is a scientific advisor to Ditto Labs and Cloudtags, and has worked closely with Facebook, Yahoo, Microsoft, IBM, Intel, Cisco, Oracle, SAP and many other leading Fortune 500 firms on realizing business value from big data analytics, social media and IT investments. He is currently a general partner at Manifest Capital, a growth equity fund focused on technology driven investments.
Sinan’s research has won numerous awards including the Microsoft Faculty Fellowship, the PopTech Science Fellowship, an NSF CAREER Award, a Fulbright Scholarship and seven “Best Paper” awards. He is a founding organizer of the Workshop on Information in Networks (WIN) at NYU and the Conference on Digital Experimentation (CODE) at MIT and was named one of the “World’s Top 40 Business School Professors Under 40” in 2014. He is a frequent speaker at thought-leading events such as Data Gotham, TEDxSiliconValley, Wired’s “Nextwork” and PopTech. His work is often featured in popular press outlets such as the Economist, the New York Times, Businessweek, Wired, Fast Company and CIO Magazine.
Sinan is a Phi Beta Kappa graduate of Northwestern University, holds Master’s degrees from the London School of Economics and Harvard University, and received his PhD from MIT. In his spare time, he cooks, skis and tells jokes about his own cooking and skiing. His most recent hobby is learning from his three-year-old son.
Website
http://web.mit.edu/sinana/www/
Date
Monday, Sept 19, 2016, 15:00-16:00
Location
Kresge Auditorium
