Online Causal Inference for Advertising in Real-Time Bidding Auctions

The authors thank the editor, Olivier Toubia, the associate editor, and two anonymous reviewers for detailed comments and feedback; Nan Xu for close collaboration at earlier stages of this paper; Tong Geng, Jun Hao, Xiliang Lin, Lei Wu, Paul Yan, Bo Zhang, Liang Zhang, and Lizhou Zheng from JD.com for their collaboration; seminar participants at Cornell Johnson, Berkeley Department of Electrical Engineering and Computer Sciences, Stanford Graduate School of Business: Operations, Information & Technology/Marketing, University of California San Diego Rady, Yale School of Management, and Insper; at the 2019 Conference on Structural Dynamic Models (Chicago Booth), the 2019 Midwest Industrial Organization Fest, the 2020 Conference on Artificial Intelligence, Machine Learning, and Business Analytics (Temple Fox), the 2020 Marketing Science Conference, the May 2021 Quantitative Marketing and Economics Rossi Seminar, and the 18th Summer Institute in Competitive Strategy Conference; Mohsen Bayati, Rob Bray, Isa Chaves, Shi Dong, Yoni Gur, Yanjun Han, Günter Hitsch, Lalit Jain, Blake McShane, Kanishka Misra, Sanjog Misra, Rob Porter, Adam Smith, Raluca Ursu, Ben Van Roy, and Stefan Wager in particular for helpful comments; and Caroline Wang and especially Vitalii Tubdenov for excellent research assistance. The authors have no funding or competing interests to declare. This paper was previously circulated under the title “Online Inference for Advertising Auctions.”