Matching Mobile Applications for Cross-Promotion

• Published in: Information systems research 2020-09, Vol.31 (3), p.865-891
• Main Authors: Lee, Gene Moo, He, Shu, Lee, Joowon, Whinston, Andrew B.
• Format: Article
• Language: English
• Subjects: Advertising; Advertising campaigns; algorithm; Algorithms; Applications programs; Cable television broadcasting industry; Computer simulation; Consumers; cross-promotion; Decisions; deferred acceptance; Dirichlet problem; Downloading; Electronic commerce; Empirical analysis; Machine learning; Market strategy; Matching; mobile analytics; Mobile applications; Mobile computing; Prediction models; Privacy; Product choice; Psychology; search cost; Similarity; Software; topic modeling; two-sided platform; User behavior; Wireless telephone software
• ISSN: 1047-7047; 1526-5536
• DOI: 10.1287/isre.2020.0921

As the mobile app market grows rapidly, with millions of apps and billions of users, search costs are increasing tremendously. Similar to the case of recommender systems, the challenge is how apps can be recommended to the right users and how consumers can find the right apps. This paper studies a new mobile app ad framework, cross-promotion (CP), which is to promote new “target” apps within other “source” apps. With unique random matching experiment data, we empirically test the important determinants of ad effectiveness. We then propose a machine-learning-based framework to optimally match source apps to target apps to improve ad effectiveness in terms of app downloads and postdownload usages. The simulation results show that app analytics capability is essential in building accurate prediction models and in increasing ad effectiveness of CP campaigns and that, at the expense of privacy, individual user data can further improve the matching performance. The paper has important managerial implications because it provides direct guidance to better utilize CP for app developers and to leverage data analytics and machine-learning models for platform managers. It also provides policy implications on the trade-off between utility and privacy in the growing data economy. The mobile applications (apps) market is one of the most successful software markets. As the platform grows rapidly, with millions of apps and billions of users, search costs are increasing tremendously. The challenge is how app developers can target the right users with their apps and how consumers can find the apps that fit their needs. Cross-promotion, advertising a mobile app (target app) in another app (source app), is introduced as a new app-promotion framework to alleviate the issue of search costs. In this paper, we model source app user behaviors (downloads and postdownload usages) with respect to different target apps in cross-promotion campaigns. We construct a novel app similarity measure using latent Dirichlet allocation topic modeling on apps’ production descriptions and then analyze how the similarity between the source and target apps influences users’ app download and usage decisions. To estimate the model, we use a unique data set from a large-scale random matching experiment conducted by a major mobile advertising company in Korea. The empirical results show that consumers prefer more diversified apps when they are making download decisions compared with their usage decisions