A Framework for adaptive user interface generation based on user behavioural patterns

Abstract

The concept of adaptivity is crucial in enterprise software systems with a large user base. Adaptive user interfaces (AUI) is an emerging research area that enables customized user experience based on user activities. Most of the existing studies that are in the conceptual level do not provide production level adaptivity for mainstream user interaction. This paper presents a generic software platform for automatic AUI generation by analyzing user behaviour patterns and customizing web user interfaces using machine learning. AdaBoost classifier showed 100% accuracy for large UI components and user scenarios (n=800). The AUI generator supports the configuration and automation of capturing user behaviour, data storage, processing, querying analysis results and dynamic rendering of the user interface. AUI platform had SUS value of 80.75. The SUS scores for the UIs without AUI was 57.3 and with AUI scored 64.35 on average. The proposed AUI platform provides production level UI design means to meet dynamic adaptability on user traits.