Data-Driven Promotion Planning for Mobile Applications

The mobile app market is one of the fastest growing segments of the media and entertainment industry. After an app is introduced, the biggest challenge facing app developers is how to get consumers to download their apps. Running price promotions is one of the common approaches app developers use to increase downloads; however, in practice, app developers are running these promotions in a rather unstructured and ad hoc manner. In this paper, we propose a two-step data analytic approach for mobile apps' promotion planning. In the first step, we use historical sales data to empirically estimate the app demand function and quantify the effect of price promotions on download volume. The estimation results reveal two interesting characteristics of the relationship between price and download volume of mobile apps: (1) the magnitude of the promotion effect is changing within a multi-day promotion; and (2) due to the visibility effect (i.e., apps ranked high on the download chart are more visible to consumers), the download volume remains at a relatively high level after a promotion ends. Based on the empirically estimated demand function, we formulate the app promotion optimization problem into a Longest Path Problem. To deal with the tractability of the Longest Path Problem, we then propose a Moving Planning Window heuristic that sequentially solves a series of sub-problems with a shorter time horizon to construct a promotion policy. Our heuristic promotion policy consists of shorter and more frequent promotions, and we show that the proposed policy can increase the app lifetime revenue by around 10%. Our two-step approach bridges the theoretical and empirical literature of promotion planning and demonstrates how to combine econometric analysis and optimization techniques to solve real-world promotion planning problems.