To remove or not remove Mobile Apps? A data-driven predictive model approach

TL;DR

This paper introduces a data-driven predictive model using machine learning to determine whether mobile apps will be removed from the Google Play Store, aiding developers and users by providing insights into app longevity.

Contribution

It presents a novel predictive approach with two models based on different feature sets, achieving high accuracy in forecasting app removal from the store.

Findings

Achieved AUC of 0.792 with user-centered model

Achieved AUC of 0.762 with developer-centered model

Compiled a new dataset of 870,515 apps from Google Play Store

Abstract

Mobile app stores are the key distributors of mobile applications. They regularly apply vetting processes to the deployed apps. Yet, some of these vetting processes might be inadequate or applied late. The late removal of applications might have unpleasant consequences for developers and users alike. Thus, in this work we propose a data-driven predictive approach that determines whether the respective app will be removed or accepted. It also indicates the features' relevance that help the stakeholders in the interpretation. In turn, our approach can support developers in improving their apps and users in downloading the ones that are less likely to be removed. We focus on the Google App store and we compile a new data set of 870,515 applications, 56% of which have actually been removed from the market. Our proposed approach is a bootstrap aggregating of multiple XGBoost machine learning classifiers. We propose two models: user-centered using 47 features, and developer-centered using 37 features, the ones only available before deployment. We achieve the following Areas Under the ROC Curves (AUCs) on the test set: user-centered = 0.792, developer-centered = 0.762.