Carrere and Gottman(1999) also indicated ''video cameras were able to predict the outcome of that marriage after six years. Using machine learning coupled with computer vision allows computers to cause this human cognitive process; models are trained on a short sample of facial features and those features automatically predict future behaviors. Computers were used in place of human coders to detect vocal behaviors ( e.g. time spent speaking, influence over conversation partners, variation in pitch and volume and behavior mirroring) during a negotiation task. Their results imply that the speech features extracted during the first five minutes of negotiation are highly predictive of future outcomes.'' The researchers also noted that using computers to code speech features offers advantages such as high test-retest reliability and real time feedback. As a cost-effective and relatively accurate method to detect, track and create models for behavior classification and prediction, automatic facial expression analysis has the potential to be applied to multiple disciplines. Capturing behavioral data from participants may be a more accurate representation of how and what they feel, and a better alternative to self-report questionnaires that interrupt participants' affective cognitive processes and are subject to bias .Our model goes beyond to predict the future behavior within a given task ( e.g. a virtual car accident or an error in performance). This opens up the possibility of such models becoming a common methodology in social scientific and behavioral research.