The increase in the adoption of Machine Learning (ML) algorithms has shown a clear indication of its effectiveness, techniques, and framework in solving robust problems. There are three categories under which Machine Learning is broadly divided, namely, reinforcement learning, unsupervised learning, and supervised learning. In this study, an attempt has been made to use supervised Machine Learning algorithms as they are seen as an important aspect of solving classification-related problems. The dataset that has been generated from a Student Modeling engine has been employed to compare the efficiency and accuracy of its classification. Three ML algorithms, namely, Random Forest (RF), K-Nearest Neighbor (KNN), and Neural Network were used to classify the dataset that was obtained from the intervention of the student modeling engine with 104 students. For two of the classification algorithms, Random Forest and K-Nearest Neighbor Python coding were used to finding the accuracy score, while for data obtained from Neural Network classification, data were subjected to SPSS statistical analysis. The comparison of the three Machine Learning algorithms showed a lower accuracy score for the Random Forest algorithm at 62% next to K-Nearest Neighbor and a higher accuracy score for the Neural Network algorithm at 79.8%. The findings of this study showed that although the classification accuracy score for Neural Network seems to be higher it still needs further confirmation from a larger dataset and also all three algorithms tested for their accuracy score under the same circumstances using Python programming.