Student Performance Prediction using Multi-Layers Artificial Neural Networks: A Case Study on Educational Data Mining

In recent years, Neural Network (NN) has seen widespread and successful implementations in a wide range of data mining applications, often surpassing other classifiers. This study plans to research of NN that are a fitting classifier to foresee understudy execution from Learning Management System information with regards to Educational Data Mining. The dataset utilized for this examination is a Moodle log document containing log data around 900 understudies more than 10 college classes. To assess the applicability of Neural Networks, two case studies compare their predictive performance on this dataset. The features used for training originate from LMS data obtained during the length of each course, and range from usage data like time spent on each course page, to grades obtained for course assignments and quizzes. After training, the Neural Network outperforms all six classifiers in terms of accuracy and is on par with the best classifiers in terms of recall. We also assessed the effect course predictors have on predictive performance by leaving out the course identifiers in the data. This does not affect predictive performance of the classifiers. Furthermore, the Neural Network is trained on individual course data to assess difference in classification performance between courses. The results show that half of these course classifiers better generally trained classifiers. The importance of individual predictors used for classification was also investigated, with previously obtained grades contributing most to successful predictions. We can conclude that the proposed neural network architecture works well with the selecting the feature data sets. It seems to the results, accuracy in student performance prediction in feature vector has been achieved and satisfactory through appropriate classification to take better decision for efficient prediction of student performance.