This research aims to enhance the achievement of the students on their study plan. The problem of the students in the university is that some students cannot design the efficient study plan, and this can cause the failure of studying. Machine Learning techniques are very powerful technique, and they can be adopted to solve this problem. Therefore, we developed our techniques and analyzed data from 300 samples by obtaining their grades of students from subjects in the curriculum of Computer Science, Faculty of Science and Technology, Sakon Nakhon Rajabhat University. In this research, we deployed CGPA prediction models and K-means models on 3rd-year and 4th-year students. The results of the experiment show high performance of these models. 37 students as representative samples were classified for their clusters and were predicted for CGPA. After sample classification, samples can inspect all vectors in their clusters as feasible study plans for next semesters. Samples can select a study plan and predict to achieve their desired CGPA. The result shows that the samples have significant improvement in CGPA by applying self-adaptive learning according to selected study plan.