Analysis of Students' Performance by Using Different Data Mining Classifiers

Abstract

Abstract-Data mining is the analysis of a large dataset to discover patterns and use those patterns to predict the likelihood of the future events. Data mining is becoming a very important field in educational sectors and it holds great potential for the schools and universities. There are many data mining classification techniques with different levels of accuracy. The objective of this paper is to analyze and evaluate the university students' performance by applying different data mining classification techniques by using WEKA tool. The highest accuracy of classifier algorithms depends on the size and nature of the data. Five classifiers are used NaiveBayes, Bayesian Network, ID3, J48 and Neural Network Different performance measures are used to compare the results between these classifiers. The results shows that Bayesian Network classifier has the highest accuracy among the other classifiers.

Electrolab: A New Dataset for Educational Data Mining

“…In the study of Almarabeh [17], Naive Bayes, BayesNet, ID3, C4.5 (J48), and Neural Network (NLP) classification algorithms were used on the dataset of 225 students records. This dataset contains the following attributes: midterm marks, assignment performance, attendance, seminar performance, lab experiments, project performance, workshop and final marks.…”

Prediction Model for Classifying Students Based on Performance using Machine Learning Techniques

“…The dependency among random variables is depicted by using directed acyclic graphs, where the nodes in the graph represent the random variables. The dependency of random variables is depicted when a connection exists between a node and an arc [6]. Govindaswamy and Velmurugan (2017) used classification and clustering algorithms such as C4.5, Expectation Maximization, k-nearest neighbour, k-means and Naïve Bayes for predicting the performance of students.…”

On Data Protection Regulations, Big Data and Sledgehammers in Higher Education

“…Higher Education institutions have not been alien to the discussions, as some scholars argued that gathering as much information as possible about university students, professors and administration staff could enable deep analysis and, thereby, proactive actions in student attention, course planning and resource management [4][5][6]. In this line, there have been numerous studies in the recent past about predicting student outcomes using Artificial Intelligence (AI) techniques [7][8][9][10][11][12][13][14][15][16][17] and it is generally assumed that the more abundant the data, the more accurate the predictions.…”

“…Our experiment consisted in performing a scan of hyperparameters for a Multi-Layer Perceptron (MLP) neural network, in search for the configuration that attained the greater accuracy in predicting academic outcomes from the socio-economic data. We chose the MLP for being one of the best understood machine learning models, commonly used in the related literature [18,19]; its best configuration would be used as a benchmark for the comparison of other techniques, including the ones used in References [7][8][9][10][11][12][13][14][15][16][17] and more advanced neural network schemes. However, the scan of hyperparameters revealed no correlations or dependencies between the input variables and the chosen metrics in any case, showing that-at least for the UPS and alike settings-there is no actual gain from applying machine learning techniques on extensive socio-economic data.…”

“…Another comparison was made in Reference [9] on a dataset containing 225 student records, with 10 attributes of academic performance each. Once again, a Bayesian network (92% accuracy) turned out to be slightly better than other classifiers (Naive Bayes, ID3 and J48) and than the Multi-Layer Perceptron.…”