Mixed-Initiative Interface Personalization as a Case Study in Usable AI

Interface personalization aims to streamline the process of working in a feature-rich application by providing the user with an adapted interface tailored specifically to his/her needs. The MICA (Mixed-Initiative Customization Assistance) system explores a middle ground between two opposing approaches to personalization: (1) an adaptable approach, where personalization is fully user controlled and (2) and adaptive approach, where personalization is fully system controlled. We overview MICA’s strategy for providing user-adaptive recommendations to help users decide how to personalize their interfaces. In doing so, we focus primarily on how MICA handles threats to usability that are often found in adaptive interfaces including obtrusiveness and lack of understandability and control. We also describe how we evaluated MICA and highlight results from these evaluations.