A computing system (e.g., a cloud server that hosts an application store) may predict the effect of modifying marketing assets (e.g., text, an image, a screenshot, a description, a video, etc.) of an application (hereinafter referred to as an “app”) on acquisitions (e.g., installations) for the app. The computing system may generate these predictions based on historical performance data (e.g., data relating to modifications to one or more marketing assets of the app and to acquisitions for the app) of marketing assets for a variety of types (e.g., lifestyle apps, social media apps, utility apps, productivity apps, entertainment apps including games, etc.) of apps on the app store. In some examples, the historical performance data may include the origin country, language, device type, purchase history, acquisition history, and/or the like of potential customers (e.g., customers of the app) such that the predictions generated by the computing system may be based on one or more of those factors. The computing system may then provide these predictions to a user (e.g., an app developer) of the application store to help (e.g., by providing benchmarks and/or recommendations) the user modify the marketing assets of the user’s app in a manner predicted to increase acquisitions for the user’s app in the app store. For example, the computing system may cause the user’s computing device (e.g., a smartphone, a tablet, a laptop) to display a statistical model (e.g., a cat and whisker plot, a bar graph, etc.) indicating the relationship between modifying one or more marketing assets and acquisitions for any type of app. The computing system may also provide statistics such as the average acquisition, the range of acquisition, the distribution of acquisition, the standard deviation of acquisition, and/or the like. Such statistics may represent acquisition benchmarks for guiding the user in modifying the user’s marketing assets.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Suppe, Steve; Davis, Mike; and Cheung, Jonathan, "DATA DRIVEN APPLICATION STORE LISTING OPTIMIZATION", Technical Disclosure Commons, (January 29, 2021)