Cold Start on Online Advertising Platforms: Data-Driven Algorithms and Field Experiments
Title： Cold Start on Online Advertising Platforms: Data-Driven Algorithms and Field Experiments
Speaker：Renyu Zhang（Assistant Professor, NYU Shanghai）
Host：Shan Wang（Assistant Professor, Lingnan College, Sun Yat-sen University）
Time and Date：October 30th, 2020 (14:30-16:00)
Location：Room 402, MBA Building
Language：English+Chinese
Abstract：：
Cold start describes a commonly recognized challenge in online advertising platforms: With limited data, the machine learning system cannot accurately estimate the click-through rates (CTR) nor the conversion rates (CVR) of new ads and in turn cannot efficiently price these new ads or match them with platform users. Unsuccessful cold start of new ads will prompt advertisers to leave the platform and decrease the thickness of the ad marketplace. To address the cold start issue for online advertising platforms, we build a data-driven optimization model that captures the essential trade-off between short-term revenue and long-term market thickness of advertisement. Based on duality theory and bandit algorithms, we develop the Shadow Bidding with Learning (SBL) algorithm with a provable regret upper bound of $O(T^(2/3)K^(1/3)(log(T)^(1/3)d^(1/2)), where K is the number of ads and d is the effective dimension of the underlying machine learning oracle for predicting CTR and CVR. Furthermore, our proposed algorithm can be straightforwardly implemented in practice with minimal adjustments to a real online advertising system. To demonstrate the effectiveness of our algorithm, we collaborate with a large-scale online video sharing platform to conduct novel two-sided randomized field experiments. Our experimental results show that the proposed algorithm could substantially increase the cold start success rate by 61.62% while only compromising the short-term revenue by 0.717%, and consequently boost the total objective value by 0.147%. Our study bridges the gap between the bandit algorithm theory and the practice of ads cold start, and highlights the significant value of well-designed cold start algorithms for online advertising platforms.
Introduction of the Speaker：
Renyu (Philip) Zhang, PhD
Assistant Professor of Operations Management
NYU Global Network Assistant Professor
New York University Shanghai
Affiliations:
NYU Stern Department of Technology, Operations, and Statistics
NYU Shanghai Center for Business Education and Research
NYU Shanghai Center for Data Science and Artificial Intelligence
Curriculum Vitae (Last update: October 2020)
About Me
I am a scholar, a teacher, and a practitioner in data science and operations research. I have been an Assistant Professor of Operations Management at New York University Shanghai since August 2016. I am also affiliated with the operations management group at NYU Stern School of Business. My research addresses fundamental operations issues under the emerging trends in technology, marketplaces, and society. I am particularly enthusiastic about developing data-driven optimization and randomized experiment (a.k.a. A/B testing) methodologies to evaluate and optimize the operations strategies in the contexts of online platforms and marketplaces, sharing economy, and social networks, especially their recommendation, advertising, and pricing policies. My research works (downloadable here) have appeared in Operations Research and Manufacturing & Service Operations Management, and have been recognized by various research awards of the INFORMS and POMS research communities. My research projects have been funded by NSFC, SMEC, and STCSM.
In addition to my scholarly endeavor, I am also interested in creating a broader impact by connecting knowledge and practice. I am an economist and Tech Lead at Kwai, developing and implementing economics and data science frameworks to evaluate and optimize the ecosystem of the large-scale online video-sharing and live-streaming platform, its recommender system and advertising platform in particular.
Prior to joining NYU Shanghai, I obtained my PhD degree in Operations Management at Olin Business School, Washington University in St. Louis in May 2016 under the supervision of Professor Nan Yang and Professor Fuqiang Zhang. I got my B.S. degree in mathematics at School of Mathematical Sciences, Peking University in July 2011.
