Adaptive User Interface for Mobile Banking Apps: Enhancing UX through Machine Learning

Mobile banking is becoming more and more popular as people use their smartphones to easily manage their finances. Banks offer these services through apps, making them simple and convenient for users. However, the User Interface (UI) of these apps often lacks personalization, frequently resulting in a worse User Experience (UX). In this research, an adaptable UI framework following a Machine Learning (ML) approach for mobile banking apps is proposed to improve the UX through personalization. For this, synthetic user data, specifically user interactions (tapping behavior) within the app, was collected and analyzed to identify user behavior. Based on user patterns, the app dynamically changed its UI to align with individual preferences. A prototype was developed using both linear adaptation and ML-based approaches. The effectiveness, efficiency, and user satisfaction metrics of this personalized app were evaluated through a user study. The evaluation findings demonstrated that the personalized mobile banking app offered a significantly improved UX compared to traditional static interfaces.