Graduation is a series of processing stages that must be passed by each student, one of graduation requirement must complete the courses with a pre-determined amount, carrying out field work practice, research proposal exam, finalexam and must complete several requirements and other requirements which are set by the college. This process should be completed within the allotted time, if not, the student will be drop-out declared. Therefore, it needs a system that can predict and evaluate the history of student course that history has been made to optimize the learning process of the next lecture. Input of this system is the master's student, student academic data, and historical data subjects which has been pursued by the student. The input data will be processed by using the techniques of data mining with C4.5 algorithm. The outputs of this system of classification is in the form of students' academic performance that predicted their graduation and providing recommendations for graduation process timely or in the most appropriate time with the optimal result based on historical subjects that have been taken.Testing on training data student sets produced values of precision, recall, and accuracy for C4.5 mining respectively 100%, 50%, and 75%.