What People Like in Mobile Finance Apps - An Analysis of User Reviews

Even though app store reviews provide highly valuable information on how people use mobile apps and what they expect from them, the systematic, timely analysis of an ever-growing volume of such unstructured reviews across many apps remains a challenge. We analyzed more than 300' 000 review sentences belonging to 1' 610 finance apps using a machine learning-based approach to investigate the impact that different aspects of finance apps have on their ratings. Additionally, we manually categorized all apps into sub-categories such as payment or trading apps to discuss our findings on an extra level of detail. This work illustrates how different aspects of mobiles apps affect their ratings, how this varies across sub-categories, and discusses the role of privacy, user interfaces, signup experiences, notifications, when the use of location services may be appropriate, and other aspects of mobile finance apps, to provide detailed insights into users' expectations and perception of finance apps.