Predicting Student Academic Performance using Data Generated in Higher Educational Institutes

Meghji, Areej Fatemah; Mahoto, Naeem Ahmed; Unar, Mukhtiar Ali; Shaikh, Mohammad Abuzar

doi:10.17993/3ctecno.2019.specialissue2.366-383

Cited by 7 publications

(18 citation statements)

References 13 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, Cao et al [1] proved that there was a significant correlation between the regularity of campus life and academic achievement by defining quantitatively two high-level behavior characteristics, orderliness and diligence. A recent study [12] examined the performance of a broad range of classification techniques to find a qualitative model for the student performance prediction problem by using students' behavior data. A previous study [13] investigated and determined significant behavior indicators from Learning Management System (LMS) platform data regarding online course achievement.…”

Section: Student Performance Predictionmentioning

confidence: 99%

Student Performance Prediction with Short-Term Sequential Campus Behaviors

Wang

Guo

et al. 2020

Information

View full text Add to dashboard Cite

As students’ behaviors are important factors that can reflect their learning styles and living habits on campus, extracting useful features of them plays a helpful role in understanding the students’ learning process, which is an important step towards personalized education. Recently, the task of predicting students’ performance from their campus behaviors has aroused the researchers’ attention. However, existing studies mainly focus on extracting statistical features manually from the pre-stored data, resulting in hysteresis in predicting students’ achievement and finding out their problems. Furthermore, due to the limited representation capability of these manually extracted features, they can only understand the students’ behaviors shallowly. To make the prediction process timely and automatically, we treat the performance prediction task as a short-term sequence prediction problem, and propose a two-stage classification framework, i.e., Sequence-based Performance Classifier (SPC), which consists of a sequence encoder and a classic data mining classifier. More specifically, to deeply discover the sequential features from students’ campus behaviors, we first introduce an attention-based Hybrid Recurrent Neural Network (HRNN) to encode their recent behaviors by giving a higher weight to the ones that are related to the students’ last action. Then, to conduct student performance prediction, we further involve these learned features to the classic Support Vector Machine (SVM) algorithm and finally achieve our SPC model. We conduct extensive experiments in the real-world student card dataset. The experimental results demonstrate the superiority of our proposed method in terms of Accuracy and Recall.

show abstract

Section: Student Performance Predictionmentioning

confidence: 99%

Student Performance Prediction with Short-Term Sequential Campus Behaviors

Wang

Guo

et al. 2020

Information

View full text Add to dashboard Cite

show abstract

“…Classification, a popular EDM method, involves categorizing objects into groups by identifying patterns in data. It generates a classification model based on the analysis of a labeled dataset, the model is subsequently used to classify new data items and group similar instances into a class [7,8].…”

mentioning

confidence: 99%

“…Course learning outcomes (CLOs) are specific lessons acquired from a course that students are expected to apply in subsequent circumstances, that emphasize key elements of the transition from student to professional, and that show the broad aspects of desired student skills. The mapping of CLOs to PLOs ensures that there are sufficient learning opportunities to support the acquisition of learning outcomes that meet the OBE standards [1][2][3][4][5][6][7][8][9].…”

mentioning

confidence: 99%

“…The methods employed to forecast students' PLO attainment comprise the utilization of classification techniques. Classification algorithms can be categorized into various categories based on the inherent mechanism of generating a classification model [7]. We explore eleven classification techniques to predict students' PLO attainment.…”

mentioning

confidence: 99%

“…Sequential Mining Optimization (SMO) is an algorithm for training support vector machines (SVMs) by decomposing the optimization problem into smaller sub-problems. The ensemble approach of random forest has also been applied [7].…”

mentioning

confidence: 99%

See 2 more Smart Citations

Educational Data Mining in Outcome-Based Education: An Analysis of Predictive Models for Program Learning Outcome Attainment

Agha,

Meghji,

Bhatti

et al. 2023

VAWKUM trans. comput. sci.

Self Cite

View full text Add to dashboard Cite

Outcome-based Education (OBE) is a student-centered strategy that focuses on students' performance in terms of knowledge, skills, and attitude to address academic gaps. Educational Data Mining (EDM) utilizes artificial intelligence and machine learning to analyze student data and boost academic achievements. Experimenting with student academic data of 397 first-year students of Mehran University of Engineering and Technology, covering nine courses and spanning two semesters, this research proposes a prediction mechanism to help anticipate student academic outcomes at an early stage during their university degree. The aim of this research is threefold. First, an exploration of EDM-based classification to predict OBE-based Program Learning Outcome (PLO) attainment. Second, the investigation of imbalanced class distribution and the benefits of using the Synthetic Minority Over-Sampling Technique on educational data. Third, a comprehensive performance evaluation of eleven classifiers is explored in this research. The evaluation entailed the use of accuracy, Kappa, recall, and precision to assess classifier performance on both balanced and unbalanced class distributions. Although several classifiers were found to be competent in handling educational data for OBE-PLO prediction, the Random Forest exhibited superior performance with an accuracy of 76.88% and a Kappa score of 0.727.

show abstract