This research aims to develop a system based on ACT-R cognitive architecture to prevent rumination. The proposed system consists of two sub-systems: data collection sub-system and distraction sub-system. The former collects searching data immediately after the individual visits a website. The latter includes an ACT-R cognitive model that utilizes such data as well as physiological data directly from the individual to predict rumination while searching through websites. In addition to predicting rumination, it provides an implicit intervention for rumination based on a concept of nudge. While a product image on the screen displays on the screen, after rumination is detected, the system changes the image to mildly intervene not to keep ruminating.