This study is to design a brainwave-eye tracking preference correlations model by utilizing user’s brainwave information and eye-tracking behaviors. We collect users’ brainwave and eye-tracking data by utilizing electroencephalography (EEG) and eye tracking devices. After analyzing the collected data, we extract several features such as concentrating, wandering mind, or gazing time or gazing positions into a back-propagation neural networks (BPNN) model to portrait the user’s brainwave-eye tracking preference correlations based on brainwave signals and eye tracking behaviors, thereby designing and developing the smart phone information recommender system. The experimental results show that the recommender system combined with the brainwave analysis and eye tracking can achieve 79% accuracy, significantly higher than only using brainwave or eye tracking information. This research has highlighted a future direction for detecting preference research and development on brainwave and eye-tracking design.