Jill Freyne (CSIRO)

Title: Engaging users through social recommender systems


Much of the focus when evaluating recommender system algorithms focuses on direct measurable impacts such as increased accuracy, diversity, product sales and click throughs, but the impact of a recommender system on an online or mobile service is far greater than these metrics suggest . In this talk I will discuss the broad impact of recommender systems, in particular social recommender systems, on user experience, user engagement with services and systems. I will draw upon my own work on social networking and behaviour change and bring in the work of others to illustrate the true impact of recommender systems in online and mobile systems.


Jill Freyne is a Senior Research Scientist and team leader of the Engagement and Effectiveness team in the eHealth Research Program at CSIRO. Jill received her PhD from University College Dublin, where her research focused on collaborative, community based web search. Jill continued her research into personalisation, social networks and recommender technology as a Postdoctoral Fellow at the Clarity Centre for Sensor Web technologies and IBM Research in Cambridge, MA where she worked primarily on influence in social networking. At CSIRO Jill’s research focuses on recommender and persuasive technologies to impact attitude and behaviour in the health domain. Jill is the author of over 60 publications published in top quality journals and conferences. She holds a strong international reputation and has organised several national and international conferences, as well as several workshops on Recommender System and Social Media. Jill is the Program Co-Chair of the 10th ACM conference on Recommender Systems and serves as a senior PC member of IJCAI, IUI and RecSys and has reviewed for many journals and conferences. Jill has taught courses on information retrieval, recommender systems and social media.

Ya Xu (Linkedin)

Title: A/B testing challenges in large social network


A/B testing, also known as controlled experiments, is widely used among online websites, including social network sites such as Facebook, LinkedIn, and Twitter to make data-driven decisions. At LinkedIn, we have seen tremendous growth of experiments over time, with now over 400 concurrent experiments running per day.  Many of the challenges we face as we scale our experimentation program arise particularly because LinkedIn is a member-based social network (we call our logged-in users “members”). In this talk, we focus on how we address these challenges as LinkedIn embraces A/B testing as the driver for innovation, from both the infrastructure and culture perspectives.

Bio: Ya has been working in the domain of online A/B testing for over 5 years. She has built and led the experimentation team to create a world-class A/B testing platform and culture @ LinkedIn. Before LinkedIn, she worked at Microsoft Bing where she focused on advancing A/B methodologies. She holds a PhD in Statistics from Stanford University. She is a frequent speaker at top-tier conferences worldwide, including WWW, WSDM, KDD and RecSys.