Adaptive User Interface Agent for Personalized Public Transportation Recommendation System: PATRASH

Public transportation guidance services, which are widely used nowadays, support our daily lives. However they have not fully been personalized yet. Regarding personalized services, an adaptive user interface plays a crucial role. This paper presents an Adaptive User Interface (AUI) agent of our personalized transportation recommendation system called PATRASH. To design and implement the agent, first, we collected and analyzed public transportation usage histories of 10 subjects so as to confirm the possibilities and effectiveness of the personalized route recommendation function. Then we propose a method to deal with user histories and evaluate the effectiveness of the proposed method based on click costs, comparing with two major transportation guidance systems in Japan. We also propose a decision-tree-based route recommendation method. The experimental results illustrate the effectiveness of the proposed method.