The authors thank Rob Donnelly, Elea Feit, Jim Griffin, Bruce Hardie, Günter Hitsch, Yufeng Huang, Unnati Narang, and Max Pachali for helpful comments and seminar participants at CREST, the Frankfurt School of Finance and Management, Penn State, Temple University, UCL, UC Riverside, University of Illinois at Urbana-Champaign, University of Rochester, Wirtschaftsuniversität Wien, and the European Quant Marketing Seminar, as well as participants at the 2021 Marketing Science Conference, the 26th International Panel Data Conference, the KDD ’21 Workshop on Machine Learning for Consumers and Markets, the 2021 CESifo digitization area meeting, and DAGStat 2022. The authors also thank IRI for making the data available. All estimates and analysis in this paper based on data provided by IRI are by the authors and not by IRI. All errors are our own. Authors are listed in reverse alphabetical order. All authors contributed equally to this work.