Speakers: David Banks, Duke University

An Overview of the Computational Advertising Landscape

Nathaniel Stevens, University of Waterloo

Computational Advertising and the Design of Experiments

Hongxia Yang, Alibaba DAMO Academy

Towards the Next Generation of AI with its Applications in Practice

Diversity: Hongxia Yang is female, David Banks and Nathaniel Stevens are male. David Banks is from the USA, Nathaniel Stevens is Canadian, Hongxia Yang is Chinese. David Banks is fairly senior, the other speakers are relatively junior---Nathaniel is an Assistant Professor. Hongxia Yang works industry.

Justification: Computational advertising refers to all the processes involved in determining when to display an on-line ad, how to display it, and what to show. It is estimated to account for $566 billion dollars in the U.S. economy alone, and that figure is growing rapidly, and all over the world. It is changing the way commerce works. 

Google runs 50 to 200 adaptive designed experiments at a time, and Facebook (Meta) runs tens of thousands of experiments---most of these aim at finding the most compelling ads for fine-grained demographic groups. Ads become stale over time, so process monitoring techniques are pertinent. One needs predictive analytics to decide which ad to show to a user, and that often requires a sophisticated model to estimate the probability of click-through. Spatio-temporal models are relevant; e.g., ads for pizza are more effective at certain times of the day and in certain parts of the world. Marketing based on dynamic pricing poses optimization problems that can be addressed through dynamic programming.

Statisticians have much to contribute to the theory and practice of computational advertising. Our profession needs to become more engaged.

David Banks:  This is an overview of the complex ecosystem of modern on-line advertising.  It will focus on the statistics behind different kinds of recommender systems, as well as topics related to process monitoring of ad success, clickthrough prediction, and optimal contract fulfillment.

Nathaniel Stevens:  On-line advertisers run hundreds of designed experiments today.  These experiments can be quite complex multiarmed bandits that gain millions of data points within a few minutes.  But there are new challenges that arise from interactions among so many experimental arms, incomplete information about users, and explore-exploit tradeoffs.

Hongxia Yang:  Artificial intelligence has reached or surpassed human standards in the perceptual intelligence fields such as "listening, speaking, and seeing", but it is still in its infancy in the field of cognitive intelligence that requires external knowledge, logical reasoning, or domain migration. After long-term exploration and verification of large-scale online businesses such as Taobao and Alipay, we have built a "super brain" through the extremely large scale pre-training model M6, and built "flexible limbs" through the edge-cloud collaboration platform Gemini, to fully present the comprehensive picture of the next generation of AI. The 10 trillion M6 is currently the world’s largest pre-training model, achieving the industry’s ultimate low-carbon efficiency. Compared to GPT-3, M6 uses only 1% of the energy consumption which greatly promotes the development of ubiquitous AI. This year, M6 supported the world's largest shopping festival Double 11 for the first time. Relying on its multi-modal understanding ability, M6 greatly improved search and recommendation accuracy of Taobao and Alipay; with its smooth writing ability, M6 created scripts and copywriting for Tmall virtual streamers; depending on its generated high-definition images, M6 has been on duty in Rhino Intelligent Manufacturing and increased the efficiency of designers by 5 times. We developed Gemini, the industry's first edge-cloud collaborative learning framework with the definition of five paradigms: cloud, edge, cloud-centric, edge-centric, and edge-cloud collaboration learning modes. It not only protects data privacy, but also has outstanding performances in personalized recommendations. This talk we will include details of state-of-the-art recommendation system in practice, M6 and Gemini.

Organiser: Prof. David Banks 

Chair: Prof. Nancy Reid 

Speaker: Prof. Wenqing He 

Speaker: Prof. David Banks 

Speaker: Dr Nathaniel Stevens