Modelling and Predicting User Engagement in Mobile Applications

Tracking #: 583-1563

Responsible editor: 

Jodi Schneider

Submission Type: 

Research Paper


The mobile ecosystem is dramatically growing towards an unprecedented scale, with an extremely crowded market and fierce competition among app developers. Today, keeping users engaged with a mobile app is key for its success since users can remain active consumers of services and/or producers of new contents. However, users may abandon a mobile app at any time due to various reasons, e.g., the success of competing apps, decrease of interest in the provided services, etc. In this context, predicting when a user may get disengaged from an app is an invaluable resource for developers, creating the opportunity to apply intervention strategies aiming at recovering from disengagement (e.g., sending push notifications with new contents). In this study, we aim at providing evidence that predicting when mobile app users get disengaged is possible with a good level of accuracy. Specifically, we propose, apply, and evaluate a framework to model and predict User Engagement (UE) in mobile applications via different numerical models. The proposed framework is composed of an optimized agglomerative hierarchical clustering model coupled to (i) a Cox proportional hazards, (ii) a negative binomial, (iii) a random forest, and (iv) a boosted-tree model. The proposed framework is empirically validated by means of a year-long observational dataset collected from a real deployment of a waste recycling app. Our results show that in this context the optimized clustering model classifies users adequately and improves UE predictability for all numerical models. Also, the highest levels of prediction accuracy and robustness are obtained by applying either the random forest classifier or the boosted-tree algorithm.



  • Reviewed

Data repository URLs: 

Date of Submission: 

Saturday, June 8, 2019

Date of Decision: 

Wednesday, July 24, 2019



Solicited Reviews:



This paper studies the user engagement in mobile apps. This is an interesting problem with important practical implications. The paper investigates the predictability of when mobile app users get disengaged with apps and shows that it can achieves the engagement prediction with a good level of accuracy. It applies different prediction models and also show clustering further facilitate the prediction. The paper is interesting, but there are some limits. 

First, it only shows the predictability while doesnot show much details about the prediction itself, namely, what features would lead to the prediction. As a result, the practical implication would be limited. Also the features used in the perdition might not provide useful indication of engagement management without further investigation, such as significance test, etc. 

Second, the prediction just applies some standard models without much technical novelties (also given the practical implication can be limited given the current status of the paper (ie, lacking of details about the prediction model); it would be helpful also give more details of technical barrier of the problem and solutions. 

Third, more features would be helpful, in particular some features can explain use engagement such as version updates, similar apps in the market. App usage feature might just related to what to predict in this paper.