Prediction of Students Performance using Machine learning

Abstract

An enormous measure of computerized information is being produced over a wide assortment in the field of data mining strategies. The creation of student achievement prediction models to predict student performance in academic institutions is a key area of the development of Education Data Mining. A prediction system has been proposed by using their 10th, 12th and previous semester marks. The study is evaluated using Binomial logical regression, Decision tree, and Entropy and KNN classifier. In order to attain their higher score, this framework would assist the student to recognize their final grade and improve their academic conduct.

IntelliDaM: A Machine Learning-Based Framework for Enhancing the Performance of Decision-Making Processes. A Case Study for Educational Data Mining

“…Recent approaches in SPP reported values such as 0.94 for the F-score when using a DT classifier [33], and accuracies of 93.67% with RF [40] or 90.1% with linear support vector machines (LSVM) [41]. Logistic Regression (LR) obtains good results, with the AUC of 0.9541 and the accuracy values of 88.8% for predicting the students' status (passed/fail) and 68.7% for predicting the final grade of students [42].…”

“…There are some specific directions in the literature related to SPP: SPP of students at risk [24], [25], students' dropout prediction [26], [27], evaluation of students' performance [28], and remedial action plans [29]. According to the students' level or the educational field where SPP is needed, different features are considered to be "good predictors": grades, historical performance data [23], [30], students' demographic data [31], or students' behaviour [32] and engagement [33].…”

Using machine learning to predict low academic performance at a Nigerian university

“…Our study was different from that that of Yağcı (2022), because we used the cumulative grade point average (CGPA), which is technically a student's average of all courses, instead of a single exam grade for a subject. Dhilipan et al (2021) use four data-mining algorithms to predict the performance of students. The four algorithms used, and their levels of accuracy, are: LR (97.05%), decision tree (88.23%), entropy (91.19%), and K-NN (93.71%).…”

“…The four algorithms used, and their levels of accuracy, are: LR (97.05%), decision tree (88.23%), entropy (91.19%), and K-NN (93.71%). While the Dhilipan et al (2021) focuses on prediction of student performance in general, our study was focused more on identification of low-performing students. In our study, not all students' data was used-only the data related to low-performing students.…”

“…In our study, not all students' data was used-only the data related to low-performing students. Also, the algorithms we used differed from those used by Dhilipan et al (2021). Vergaray et al (2022) present a stacking multi-classification model for mining academic performance of students, using five classification algorithms, with their output as a feeder to the stacking model.…”